Model profile · Google

Gemini 3.1 Flash-Lite Preview

Closed weightsmid · registry tag 2026 preview

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 32.2%
Verified coverage: 32.2%
Spread: n/a
Last verified: Jun 20, 2026

textvisiondocumentaudiocode3 aliases43 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text28 benchmarks73.6%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #82 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25
Percentile: 79.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

79.5% percentile inside its fair comparison set

25Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #23 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.4%
Percentile: 92.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

92.6% percentile inside its fair comparison set

36.4%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #124 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.4%
Percentile: 58.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

58.7% percentile inside its fair comparison set

18.4%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 77.2%
Percentile: 98.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

98.1% percentile inside its fair comparison set

77.2%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #131 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.6 /1M tokens
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

52.9% percentile inside its fair comparison set

$0.6 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #112 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

59.8% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #139 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M output tokens
Percentile: 50%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

50% percentile inside its fair comparison set

$1.5 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 367.6 tokens/s
Percentile: 97.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

97.1% percentile inside its fair comparison set

367.6 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #174 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.87s
Percentile: 17.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

17.6% percentile inside its fair comparison set

5.87sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #87 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.87s
Percentile: 59%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

59% percentile inside its fair comparison set

5.87sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #54 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 83.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #70. Votes: 48525. Organization: google. License: Proprietary.

83.7% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,436

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #44 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 86.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing. Source rank: #57. Votes: 7604. Organization: google. License: Proprietary.

86.7% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,403 - 1,419

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #69 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 79.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #86. Votes: 23041. Organization: google. License: Proprietary.

79.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,428 - 1,438

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #53 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: exclude_ties. Source rank: #68. Votes: 36124. Organization: google. License: Proprietary.

84% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,422 - 1,432

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 80%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts. Source rank: #84. Votes: 30910. Organization: google. License: Proprietary.

80% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,439 - 1,449

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #80 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 75.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts_english. Source rank: #99. Votes: 15487. Organization: google. License: Proprietary.

75.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,434 - 1,446

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #73 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 77.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: instruction_following. Source rank: #92. Votes: 15755. Organization: google. License: Proprietary.

77.8% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,402 - 1,413

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 77%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: longer_query. Source rank: #89. Votes: 19177. Organization: google. License: Proprietary.

77% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,435

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #56 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 83%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: multi_turn. Source rank: #73. Votes: 8798. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,429 - 1,443

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #93. Votes: 48525. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,411 - 1,419

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing. Source rank: #71. Votes: 7604. Organization: google. License: Proprietary.

82.4% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,405

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #94 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 71.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #110. Votes: 23041. Organization: google. License: Proprietary.

71.4% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,407 - 1,417

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: exclude_ties. Source rank: #93. Votes: 36124. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,406

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 71.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts. Source rank: #111. Votes: 30910. Organization: google. License: Proprietary.

71.7% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,402 - 1,411

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #103 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts_english. Source rank: #124. Votes: 15487. Organization: google. License: Proprietary.

68.5% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,394 - 1,406

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #95 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: instruction_following. Source rank: #116. Votes: 15755. Organization: google. License: Proprietary.

71.1% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,371 - 1,382

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 69.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: longer_query. Source rank: #115. Votes: 19177. Organization: google. License: Proprietary.

69.7% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,389 - 1,400

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 79.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: multi_turn. Source rank: #82. Votes: 8798. Organization: google. License: Proprietary.

79.9% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,411 - 1,425

Coding17 benchmarks33.7%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #87 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

71.9% percentile inside its fair comparison set

24.2%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 41.9%
Percentile: 88.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

88.9% percentile inside its fair comparison set

41.9%Raw benchmark value

Coding Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35
Percentile: 45.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

45.3% percentile inside its fair comparison set

35Raw benchmark value

Agentic Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #40 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 15.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

15.2% percentile inside its fair comparison set

6Raw benchmark value

Code Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #77. Votes: 11736. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev. Source rank: #77. Votes: 11736. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,273
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev-html. Source rank: #76. Votes: 1408. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,273Raw benchmark valueCI 1,255 - 1,291

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #53 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 11.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev-react. Source rank: #66. Votes: 10288. Organization: google. License: Proprietary.

11.9% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,232 - 1,247

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 4.6%
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Google.

0% percentile inside its fair comparison set

4.6%Raw benchmark valueCI 2.5% - 6.7%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #44 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.1%
Percentile: 52.2%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Google.

52.2% percentile inside its fair comparison set

80.1%Raw benchmark valueCI 78% - 82.2%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #20 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 70%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Google.

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #46 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.8%
Percentile: 16.7%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Google.

16.7% percentile inside its fair comparison set

62.8%Raw benchmark valueCI 58.6% - 67%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #28 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.1%
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

0% percentile inside its fair comparison set

34.1%Raw benchmark valueCI 32.1% - 36%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #48 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 4.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Google.

4.1% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #83 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 74.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: coding. Source rank: #103. Votes: 13244. Organization: google. License: Proprietary.

74.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,451 - 1,464

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #106 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 67.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: coding. Source rank: #130. Votes: 13244. Organization: google. License: Proprietary.

67.2% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,406

Code Arena · Image To Webdev

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 5.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: image_to_webdev. Source rank: #22. Votes: 3742. Organization: google. License: Proprietary.

5.9% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,316 - 1,342

Reasoning / math / science8 benchmarks70.6%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #52 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.2%
Percentile: 86.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

86.2% percentile inside its fair comparison set

16.2%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #53 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82.2%
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

86.4% percentile inside its fair comparison set

82.2%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #44 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.1%
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

86.1% percentile inside its fair comparison set

1.1%Raw benchmark value

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #43 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.1%
Percentile: 52.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Google.

52.8% percentile inside its fair comparison set

81.1%Raw benchmark valueCI 77.2% - 84.9%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.2%
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Google.

70.8% percentile inside its fair comparison set

86.2%Raw benchmark valueCI 85.6% - 86.9%

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #42 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: math. Source rank: #53. Votes: 2855. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,430 - 1,453

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #46 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: math. Source rank: #57. Votes: 2855. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,445

TutorBench

SL · Reasoning / math / science · Rubric

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #10 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 51.5%
Percentile: 10%
Last updated: recent
Eligibility: preview_model

10% percentile inside its fair comparison set

51.5%Raw benchmark value

Professional reasoning27 benchmarks63.4%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #41 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 603
Percentile: 13%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

13% percentile inside its fair comparison set

603Raw benchmark value

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #19 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.2%
Percentile: 25%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

25% percentile inside its fair comparison set

12.2%Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

0% percentile inside its fair comparison set

36Raw benchmark valueCI 35 - 38

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.8%
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Google.

71.1% percentile inside its fair comparison set

83.8%Raw benchmark valueCI 83% - 84.6%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #24 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30%
Percentile: 8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Google.

8% percentile inside its fair comparison set

30%Raw benchmark valueCI 28.7% - 31.2%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #51 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.8%
Percentile: 45.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

45.1% percentile inside its fair comparison set

71.8%Raw benchmark valueCI 70.1% - 73.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #16 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.6%
Percentile: 70.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Google.

70.6% percentile inside its fair comparison set

47.6%Raw benchmark valueCI 43.5% - 51.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #49 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63.9%
Percentile: 4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Google.

4% percentile inside its fair comparison set

63.9%Raw benchmark valueCI 60.3% - 67.5%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 76.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: expert. Source rank: #84. Votes: 4298. Organization: google. License: Proprietary.

76.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,436 - 1,455

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #67 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 79.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #84. Votes: 9392. Organization: google. License: Proprietary.

79.2% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,413 - 1,426

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 83.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #68. Votes: 9892. Organization: google. License: Proprietary.

83.3% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,396 - 1,410

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_legal_and_government. Source rank: #76. Votes: 3735. Organization: google. License: Proprietary.

80.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,428 - 1,449

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #68. Votes: 7903. Organization: google. License: Proprietary.

83.3% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,459

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 81.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_mathematical. Source rank: #71. Votes: 2673. Organization: google. License: Proprietary.

81.5% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,427 - 1,451

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #54 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_medicine_and_healthcare. Source rank: #70. Votes: 3518. Organization: google. License: Proprietary.

82% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,445 - 1,466

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 78.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_software_and_it_services. Source rank: #88. Votes: 19057. Organization: google. License: Proprietary.

78.5% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,449 - 1,460

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #47 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 85.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_writing_and_literature_and_language. Source rank: #60. Votes: 11366. Organization: google. License: Proprietary.

85.8% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,413 - 1,426

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #90 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 67.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: expert. Source rank: #110. Votes: 4298. Organization: google. License: Proprietary.

67.6% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,411

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #97 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 69.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #115. Votes: 9392. Organization: google. License: Proprietary.

69.8% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,382 - 1,396

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #70 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 78.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #84. Votes: 9892. Organization: google. License: Proprietary.

78.6% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,378 - 1,392

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #80 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 73.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_legal_and_government. Source rank: #98. Votes: 3735. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,406 - 1,426

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 76.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #92. Votes: 7903. Organization: google. License: Proprietary.

76.2% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,420 - 1,435

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #70 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 77.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_mathematical. Source rank: #83. Votes: 2673. Organization: google. License: Proprietary.

77.6% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,411 - 1,436

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_medicine_and_healthcare. Source rank: #83. Votes: 3518. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,418 - 1,439

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #98 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_software_and_it_services. Source rank: #116. Votes: 19057. Organization: google. License: Proprietary.

70.2% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,408 - 1,419

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_writing_and_literature_and_language. Source rank: #70. Votes: 11366. Organization: google. License: Proprietary.

82.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,400 - 1,413

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #14 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.5%
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Google.

71.1% percentile inside its fair comparison set

49.5%Raw benchmark valueCI 42.7% - 56.4%

Search / tool use1 benchmark44.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #173 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.3%
Percentile: 44.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

44.3% percentile inside its fair comparison set

31.3%Raw benchmark value

Long context2 benchmarks64.8%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #27 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.3%
Percentile: 92.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.1% percentile inside its fair comparison set

65.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #56 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.4%
Percentile: 37.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Google.

37.5% percentile inside its fair comparison set

59.4%Raw benchmark valueCI 57.5% - 61.3%

Vision understanding18 benchmarks66.3%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #11 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.5%
Percentile: 92.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

92.6% percentile inside its fair comparison set

75.5%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 73.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #39. Votes: 21080. Organization: google. License: Proprietary.

73.4% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,229 - 1,242

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 47.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing_vision. Source rank: #37. Votes: 1269. Organization: google. License: Proprietary.

47.3% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,215 - 1,250

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #32 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,253
Percentile: 55.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: diagram. Source rank: #42. Votes: 5464. Organization: google. License: Proprietary.

55.7% percentile inside its fair comparison set

1,253Raw benchmark valueCI 1,244 - 1,263

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #35 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,224
Percentile: 68.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #45. Votes: 8741. Organization: google. License: Proprietary.

68.8% percentile inside its fair comparison set

1,224Raw benchmark valueCI 1,215 - 1,234

Vision Arena · Entity Recognition

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #4 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 90.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: entity_recognition. Source rank: #5. Votes: 140. Organization: google. License: Proprietary.

90.6% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,210 - 1,303

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 61.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: homework. Source rank: #34. Votes: 3230. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,260 - 1,283

Vision Arena · Humor

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #13 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,256
Percentile: 75.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: humor. Source rank: #16. Votes: 722. Organization: google. License: Proprietary.

75.5% percentile inside its fair comparison set

1,256Raw benchmark valueCI 1,234 - 1,279

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 61.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: ocr. Source rank: #37. Votes: 14712. Organization: google. License: Proprietary.

61.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 69.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #42. Votes: 21080. Organization: google. License: Proprietary.

69.7% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,234 - 1,247

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 50.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing_vision. Source rank: #36. Votes: 1269. Organization: google. License: Proprietary.

50.9% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,226 - 1,260

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #39 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,244
Percentile: 45.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: diagram. Source rank: #50. Votes: 5464. Organization: google. License: Proprietary.

45.7% percentile inside its fair comparison set

1,244Raw benchmark valueCI 1,235 - 1,254

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #39 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,229
Percentile: 65.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #50. Votes: 8741. Organization: google. License: Proprietary.

65.1% percentile inside its fair comparison set

1,229Raw benchmark valueCI 1,219 - 1,238

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #6 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 84.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: entity_recognition. Source rank: #7. Votes: 140. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,244 - 1,336

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #29 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,271
Percentile: 58.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: homework. Source rank: #36. Votes: 3230. Organization: google. License: Proprietary.

58.8% percentile inside its fair comparison set

1,271Raw benchmark valueCI 1,260 - 1,282

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #14 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 73.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: humor. Source rank: #17. Votes: 722. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,250 - 1,294

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: ocr. Source rank: #42. Votes: 14712. Organization: google. License: Proprietary.

52.9% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,255

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #21 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.5%
Percentile: 65.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Google.

65.5% percentile inside its fair comparison set

82.5%Raw benchmark valueCI 80.7% - 84.3%

Document understanding2 benchmarks42.8%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #18 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41
Percentile: 10.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: Google.

10.5% percentile inside its fair comparison set

41Raw benchmark valueCI 40 - 43

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #16 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68%
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Google.

75% percentile inside its fair comparison set

68%Raw benchmark valueCI 66.3% - 69.8%

Safety1 benchmark15.4%

MASK

SL · Safety · Rubric

Whether a model stays honest instead of covertly optimizing against the user.

Rank #12 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.4%
Percentile: 15.4%
Last updated: recent
Eligibility: preview_model

15.4% percentile inside its fair comparison set

48.4%Raw benchmark value

Multilingual16 benchmarks79.5%

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #47 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 84.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #58. Votes: 2656. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,469 - 1,494

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 71.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: french. Source rank: #78. Votes: 1559. Organization: google. License: Proprietary.

71.8% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,427 - 1,462

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #35 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: german. Source rank: #45. Votes: 772. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,421 - 1,465

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: japanese. Source rank: #42. Votes: 408. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,385 - 1,447

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #33 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: korean. Source rank: #40. Votes: 820. Organization: google. License: Proprietary.

84.6% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,389 - 1,433

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #50 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 83%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: russian. Source rank: #64. Votes: 5220. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,428 - 1,446

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #41 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 81.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: spanish. Source rank: #51. Votes: 1449. Organization: google. License: Proprietary.

81.3% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,424 - 1,457

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 81.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #66. Votes: 2656. Organization: google. License: Proprietary.

81.7% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,452 - 1,477

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 64.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: french. Source rank: #94. Votes: 1559. Organization: google. License: Proprietary.

64.4% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,401 - 1,436

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #32 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: german. Source rank: #41. Votes: 772. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,414 - 1,458

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 87.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: japanese. Source rank: #36. Votes: 408. Organization: google. License: Proprietary.

87.2% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,375 - 1,437

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: korean. Source rank: #37. Votes: 820. Organization: google. License: Proprietary.

86.1% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,380 - 1,424

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #51 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 82.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: russian. Source rank: #63. Votes: 5220. Organization: google. License: Proprietary.

82.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,414 - 1,431

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #52 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 76.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: spanish. Source rank: #62. Votes: 1449. Organization: google. License: Proprietary.

76.2% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,409 - 1,442

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 66.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #34. Votes: 1225. Organization: google. License: Proprietary.

66.2% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,258 - 1,302

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,286
Percentile: 64.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #35. Votes: 1225. Organization: google. License: Proprietary.

64.9% percentile inside its fair comparison set

1,286Raw benchmark valueCI 1,265 - 1,308

Source links and registry checks

official

Google Gemini models docs

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

Model profile · Google

Gemini 3.1 Flash-Lite Preview

Closed weightsmid · registry tag 2026 preview

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 32.2%
Verified coverage: 32.2%
Spread: n/a
Last verified: Jun 20, 2026

textvisiondocumentaudiocode3 aliases43 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text28 benchmarks73.6%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #82 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 25
Percentile: 79.5%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

79.5% percentile inside its fair comparison set

25Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #23 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 36.4%
Percentile: 92.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

92.6% percentile inside its fair comparison set

36.4%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #124 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.4%
Percentile: 58.7%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

58.7% percentile inside its fair comparison set

18.4%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 77.2%
Percentile: 98.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

98.1% percentile inside its fair comparison set

77.2%Raw benchmark value

Blended price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #131 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.6 /1M tokens
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

52.9% percentile inside its fair comparison set

$0.6 /1M tokensRaw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #112 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.3 /1M input tokens
Percentile: 59.8%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

59.8% percentile inside its fair comparison set

$0.3 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #139 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $1.5 /1M output tokens
Percentile: 50%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

50% percentile inside its fair comparison set

$1.5 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 367.6 tokens/s
Percentile: 97.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

97.1% percentile inside its fair comparison set

367.6 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #174 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.87s
Percentile: 17.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

17.6% percentile inside its fair comparison set

5.87sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #87 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 5.87s
Percentile: 59%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

59% percentile inside its fair comparison set

5.87sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #54 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 83.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #70. Votes: 48525. Organization: google. License: Proprietary.

83.7% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,428 - 1,436

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #44 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 86.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing. Source rank: #57. Votes: 7604. Organization: google. License: Proprietary.

86.7% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,403 - 1,419

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #69 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 79.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #86. Votes: 23041. Organization: google. License: Proprietary.

79.1% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,428 - 1,438

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #53 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 84%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: exclude_ties. Source rank: #68. Votes: 36124. Organization: google. License: Proprietary.

84% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,422 - 1,432

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 80%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts. Source rank: #84. Votes: 30910. Organization: google. License: Proprietary.

80% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,439 - 1,449

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #80 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,440
Percentile: 75.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts_english. Source rank: #99. Votes: 15487. Organization: google. License: Proprietary.

75.6% percentile inside its fair comparison set

1,440Raw benchmark valueCI 1,434 - 1,446

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #73 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 77.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: instruction_following. Source rank: #92. Votes: 15755. Organization: google. License: Proprietary.

77.8% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,402 - 1,413

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 77%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: longer_query. Source rank: #89. Votes: 19177. Organization: google. License: Proprietary.

77% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,423 - 1,435

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #56 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 83%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: multi_turn. Source rank: #73. Votes: 8798. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,429 - 1,443

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #93. Votes: 48525. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,411 - 1,419

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing. Source rank: #71. Votes: 7604. Organization: google. License: Proprietary.

82.4% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,405

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #94 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 71.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #110. Votes: 23041. Organization: google. License: Proprietary.

71.4% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,407 - 1,417

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: exclude_ties. Source rank: #93. Votes: 36124. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,396 - 1,406

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 71.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts. Source rank: #111. Votes: 30910. Organization: google. License: Proprietary.

71.7% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,402 - 1,411

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #103 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: hard_prompts_english. Source rank: #124. Votes: 15487. Organization: google. License: Proprietary.

68.5% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,394 - 1,406

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #95 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: instruction_following. Source rank: #116. Votes: 15755. Organization: google. License: Proprietary.

71.1% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,371 - 1,382

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #93 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 69.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: longer_query. Source rank: #115. Votes: 19177. Organization: google. License: Proprietary.

69.7% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,389 - 1,400

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 79.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: multi_turn. Source rank: #82. Votes: 8798. Organization: google. License: Proprietary.

79.9% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,411 - 1,425

Coding17 benchmarks33.7%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #87 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 24.2%
Percentile: 71.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

71.9% percentile inside its fair comparison set

24.2%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 41.9%
Percentile: 88.9%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

88.9% percentile inside its fair comparison set

41.9%Raw benchmark value

Coding Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #42 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35
Percentile: 45.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

45.3% percentile inside its fair comparison set

35Raw benchmark value

Agentic Index

AA · Coding · Combined

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #40 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 15.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

15.2% percentile inside its fair comparison set

6Raw benchmark value

Code Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #77. Votes: 11736. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev. Source rank: #77. Votes: 11736. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,273
Percentile: 16.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev-html. Source rank: #76. Votes: 1408. Organization: google. License: Proprietary.

16.4% percentile inside its fair comparison set

1,273Raw benchmark valueCI 1,255 - 1,291

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #53 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,240
Percentile: 11.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: webdev-react. Source rank: #66. Votes: 10288. Organization: google. License: Proprietary.

11.9% percentile inside its fair comparison set

1,240Raw benchmark valueCI 1,232 - 1,247

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 4.6%
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Google.

0% percentile inside its fair comparison set

4.6%Raw benchmark valueCI 2.5% - 6.7%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #44 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.1%
Percentile: 52.2%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Google.

52.2% percentile inside its fair comparison set

80.1%Raw benchmark valueCI 78% - 82.2%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #20 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 70%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Google.

70% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #46 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 62.8%
Percentile: 16.7%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Google.

16.7% percentile inside its fair comparison set

62.8%Raw benchmark valueCI 58.6% - 67%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #28 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.1%
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

0% percentile inside its fair comparison set

34.1%Raw benchmark valueCI 32.1% - 36%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #48 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 4.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Google.

4.1% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #83 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 74.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: coding. Source rank: #103. Votes: 13244. Organization: google. License: Proprietary.

74.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,451 - 1,464

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #106 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 67.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: coding. Source rank: #130. Votes: 13244. Organization: google. License: Proprietary.

67.2% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,393 - 1,406

Code Arena · Image To Webdev

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 5.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: image_to_webdev. Source rank: #22. Votes: 3742. Organization: google. License: Proprietary.

5.9% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,316 - 1,342

Reasoning / math / science8 benchmarks70.6%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #52 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 16.2%
Percentile: 86.2%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `hle`.

86.2% percentile inside its fair comparison set

16.2%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #53 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 82.2%
Percentile: 86.4%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

86.4% percentile inside its fair comparison set

82.2%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #44 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1.1%
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

86.1% percentile inside its fair comparison set

1.1%Raw benchmark value

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #43 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.1%
Percentile: 52.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Google.

52.8% percentile inside its fair comparison set

81.1%Raw benchmark valueCI 77.2% - 84.9%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 86.2%
Percentile: 70.8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Google.

70.8% percentile inside its fair comparison set

86.2%Raw benchmark valueCI 85.6% - 86.9%

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #42 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: math. Source rank: #53. Votes: 2855. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,430 - 1,453

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #46 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,434
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: math. Source rank: #57. Votes: 2855. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,434Raw benchmark valueCI 1,422 - 1,445

TutorBench

SL · Reasoning / math / science · Rubric

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #10 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 51.5%
Percentile: 10%
Last updated: recent
Eligibility: preview_model

10% percentile inside its fair comparison set

51.5%Raw benchmark value

Professional reasoning27 benchmarks63.4%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #41 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 603
Percentile: 13%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `gdpvalBreakdown.elo`.

13% percentile inside its fair comparison set

603Raw benchmark value

APEX-Agents-AA

AA · Professional reasoning · Objective

Long-horizon agentic task completion.

Rank #19 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 12.2%
Percentile: 25%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `apexAgents`.

25% percentile inside its fair comparison set

12.2%Raw benchmark value

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36
Percentile: 0%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

0% percentile inside its fair comparison set

36Raw benchmark valueCI 35 - 38

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #27 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.8%
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Google.

71.1% percentile inside its fair comparison set

83.8%Raw benchmark valueCI 83% - 84.6%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #24 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30%
Percentile: 8%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Google.

8% percentile inside its fair comparison set

30%Raw benchmark valueCI 28.7% - 31.2%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #51 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.8%
Percentile: 45.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

45.1% percentile inside its fair comparison set

71.8%Raw benchmark valueCI 70.1% - 73.5%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #16 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 47.6%
Percentile: 70.6%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Google.

70.6% percentile inside its fair comparison set

47.6%Raw benchmark valueCI 43.5% - 51.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #49 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 63.9%
Percentile: 4%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Google.

4% percentile inside its fair comparison set

63.9%Raw benchmark valueCI 60.3% - 67.5%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #66 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 76.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: expert. Source rank: #84. Votes: 4298. Organization: google. License: Proprietary.

76.4% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,436 - 1,455

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #67 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 79.2%
Last updated: recent
Eligibility: preview_model

79.2% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,413 - 1,426

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,403
Percentile: 83.3%
Last updated: recent
Eligibility: preview_model

83.3% percentile inside its fair comparison set

1,403Raw benchmark valueCI 1,396 - 1,410

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 80.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_legal_and_government. Source rank: #76. Votes: 3735. Organization: google. License: Proprietary.

80.9% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,428 - 1,449

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 83.3%
Last updated: recent
Eligibility: preview_model

83.3% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,444 - 1,459

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 81.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_mathematical. Source rank: #71. Votes: 2673. Organization: google. License: Proprietary.

81.5% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,427 - 1,451

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #54 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 82%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_medicine_and_healthcare. Source rank: #70. Votes: 3518. Organization: google. License: Proprietary.

82% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,445 - 1,466

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 78.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_software_and_it_services. Source rank: #88. Votes: 19057. Organization: google. License: Proprietary.

78.5% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,449 - 1,460

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #47 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 85.8%
Last updated: recent
Eligibility: preview_model

85.8% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,413 - 1,426

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #90 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 67.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: expert. Source rank: #110. Votes: 4298. Organization: google. License: Proprietary.

67.6% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,392 - 1,411

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #97 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 69.8%
Last updated: recent
Eligibility: preview_model

69.8% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,382 - 1,396

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #70 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 78.6%
Last updated: recent
Eligibility: preview_model

78.6% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,378 - 1,392

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #80 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 73.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_legal_and_government. Source rank: #98. Votes: 3735. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,406 - 1,426

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,427
Percentile: 76.2%
Last updated: recent
Eligibility: preview_model

76.2% percentile inside its fair comparison set

1,427Raw benchmark valueCI 1,420 - 1,435

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #70 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,424
Percentile: 77.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_mathematical. Source rank: #83. Votes: 2673. Organization: google. License: Proprietary.

77.6% percentile inside its fair comparison set

1,424Raw benchmark valueCI 1,411 - 1,436

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #71 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 76.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_medicine_and_healthcare. Source rank: #83. Votes: 3518. Organization: google. License: Proprietary.

76.3% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,418 - 1,439

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #98 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 70.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: industry_software_and_it_services. Source rank: #116. Votes: 19057. Organization: google. License: Proprietary.

70.2% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,408 - 1,419

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #58 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 82.4%
Last updated: recent
Eligibility: preview_model

82.4% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,400 - 1,413

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #14 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.5%
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Google.

71.1% percentile inside its fair comparison set

49.5%Raw benchmark valueCI 42.7% - 56.4%

Search / tool use1 benchmark44.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #173 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.3%
Percentile: 44.3%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

44.3% percentile inside its fair comparison set

31.3%Raw benchmark value

Long context2 benchmarks64.8%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #27 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 65.3%
Percentile: 92.1%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.1% percentile inside its fair comparison set

65.3%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #56 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59.4%
Percentile: 37.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Google.

37.5% percentile inside its fair comparison set

59.4%Raw benchmark valueCI 57.5% - 61.3%

Vision understanding18 benchmarks66.3%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #11 · Source label: Gemini 3.1 Flash-Lite

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.5%
Percentile: 92.6%
Last updated: recent
Eligibility: preview_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

92.6% percentile inside its fair comparison set

75.5%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,235
Percentile: 73.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #39. Votes: 21080. Organization: google. License: Proprietary.

73.4% percentile inside its fair comparison set

1,235Raw benchmark valueCI 1,229 - 1,242

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,233
Percentile: 47.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing_vision. Source rank: #37. Votes: 1269. Organization: google. License: Proprietary.

47.3% percentile inside its fair comparison set

1,233Raw benchmark valueCI 1,215 - 1,250

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #32 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,253
Percentile: 55.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: diagram. Source rank: #42. Votes: 5464. Organization: google. License: Proprietary.

55.7% percentile inside its fair comparison set

1,253Raw benchmark valueCI 1,244 - 1,263

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #35 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,224
Percentile: 68.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #45. Votes: 8741. Organization: google. License: Proprietary.

68.8% percentile inside its fair comparison set

1,224Raw benchmark valueCI 1,215 - 1,234

Vision Arena · Entity Recognition

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #4 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,257
Percentile: 90.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: entity_recognition. Source rank: #5. Votes: 140. Organization: google. License: Proprietary.

90.6% percentile inside its fair comparison set

1,257Raw benchmark valueCI 1,210 - 1,303

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 61.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: homework. Source rank: #34. Votes: 3230. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,260 - 1,283

Vision Arena · Humor

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #13 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,256
Percentile: 75.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: humor. Source rank: #16. Votes: 722. Organization: google. License: Proprietary.

75.5% percentile inside its fair comparison set

1,256Raw benchmark valueCI 1,234 - 1,279

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 61.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: ocr. Source rank: #37. Votes: 14712. Organization: google. License: Proprietary.

61.4% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,256

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,241
Percentile: 69.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: overall. Source rank: #42. Votes: 21080. Organization: google. License: Proprietary.

69.7% percentile inside its fair comparison set

1,241Raw benchmark valueCI 1,234 - 1,247

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,243
Percentile: 50.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: creative_writing_vision. Source rank: #36. Votes: 1269. Organization: google. License: Proprietary.

50.9% percentile inside its fair comparison set

1,243Raw benchmark valueCI 1,226 - 1,260

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #39 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,244
Percentile: 45.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: diagram. Source rank: #50. Votes: 5464. Organization: google. License: Proprietary.

45.7% percentile inside its fair comparison set

1,244Raw benchmark valueCI 1,235 - 1,254

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #39 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,229
Percentile: 65.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: english. Source rank: #50. Votes: 8741. Organization: google. License: Proprietary.

65.1% percentile inside its fair comparison set

1,229Raw benchmark valueCI 1,219 - 1,238

Vision Arena · Entity Recognition · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #6 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 84.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: entity_recognition. Source rank: #7. Votes: 140. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,244 - 1,336

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #29 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,271
Percentile: 58.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: homework. Source rank: #36. Votes: 3230. Organization: google. License: Proprietary.

58.8% percentile inside its fair comparison set

1,271Raw benchmark valueCI 1,260 - 1,282

Vision Arena · Humor · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #14 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,272
Percentile: 73.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: humor. Source rank: #17. Votes: 722. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,272Raw benchmark valueCI 1,250 - 1,294

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 52.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: ocr. Source rank: #42. Votes: 14712. Organization: google. License: Proprietary.

52.9% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,242 - 1,255

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #21 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82.5%
Percentile: 65.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Google.

65.5% percentile inside its fair comparison set

82.5%Raw benchmark valueCI 80.7% - 84.3%

Document understanding2 benchmarks42.8%

Vals Multimodal Index

VALS-AI · Document understanding · Combined

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #18 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 41
Percentile: 10.5%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_multimodal_index; provider: Google.

10.5% percentile inside its fair comparison set

41Raw benchmark valueCI 40 - 43

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #16 · Source label: google/gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68%
Percentile: 75%
Last updated: recent
Eligibility: preview_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Google.

75% percentile inside its fair comparison set

68%Raw benchmark valueCI 66.3% - 69.8%

Safety1 benchmark15.4%

MASK

SL · Safety · Rubric

Whether a model stays honest instead of covertly optimizing against the user.

Rank #12 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.4%
Percentile: 15.4%
Last updated: recent
Eligibility: preview_model

15.4% percentile inside its fair comparison set

48.4%Raw benchmark value

Multilingual16 benchmarks79.5%

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #47 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 84.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #58. Votes: 2656. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,469 - 1,494

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #62 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 71.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: french. Source rank: #78. Votes: 1559. Organization: google. License: Proprietary.

71.8% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,427 - 1,462

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #35 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: german. Source rank: #45. Votes: 772. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,421 - 1,465

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 85.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: japanese. Source rank: #42. Votes: 408. Organization: google. License: Proprietary.

85.7% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,385 - 1,447

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #33 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 84.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: korean. Source rank: #40. Votes: 820. Organization: google. License: Proprietary.

84.6% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,389 - 1,433

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #50 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,437
Percentile: 83%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: russian. Source rank: #64. Votes: 5220. Organization: google. License: Proprietary.

83% percentile inside its fair comparison set

1,437Raw benchmark valueCI 1,428 - 1,446

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #41 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 81.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: spanish. Source rank: #51. Votes: 1449. Organization: google. License: Proprietary.

81.3% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,424 - 1,457

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #55 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 81.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #66. Votes: 2656. Organization: google. License: Proprietary.

81.7% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,452 - 1,477

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #78 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 64.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: french. Source rank: #94. Votes: 1559. Organization: google. License: Proprietary.

64.4% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,401 - 1,436

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #32 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,436
Percentile: 86.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: german. Source rank: #41. Votes: 772. Organization: google. License: Proprietary.

86.9% percentile inside its fair comparison set

1,436Raw benchmark valueCI 1,414 - 1,458

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 87.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: japanese. Source rank: #36. Votes: 408. Organization: google. License: Proprietary.

87.2% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,375 - 1,437

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #30 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 86.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: korean. Source rank: #37. Votes: 820. Organization: google. License: Proprietary.

86.1% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,380 - 1,424

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #51 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,422
Percentile: 82.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: russian. Source rank: #63. Votes: 5220. Organization: google. License: Proprietary.

82.7% percentile inside its fair comparison set

1,422Raw benchmark valueCI 1,414 - 1,431

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #52 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 76.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: spanish. Source rank: #62. Votes: 1449. Organization: google. License: Proprietary.

76.2% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,409 - 1,442

Vision Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #27 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 66.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #34. Votes: 1225. Organization: google. License: Proprietary.

66.2% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,258 - 1,302

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Vision Arena chinese leaderboard.

Rank #28 · Source label: gemini-3.1-flash-lite-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,286
Percentile: 64.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `gemini-3.1-flash-lite-preview`. Category: chinese. Source rank: #35. Votes: 1225. Organization: google. License: Proprietary.

64.9% percentile inside its fair comparison set

1,286Raw benchmark valueCI 1,265 - 1,308