Model profile · Google

Gemini 2.5 Flash-Lite

Closed weightsmid · registry tag 2026 cheap

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 21.9%
Verified coverage: 21.9%
Spread: 87.1%
Last verified: Jun 20, 2026

40%bench fit

textvisiondocumentaudiocode13 aliases40 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 / text29 benchmarks57.1%

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 #280 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7
Percentile: 29.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

29.4% percentile inside its fair comparison set

7Raw 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 #203 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.3%
Percentile: 32.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

32.2% percentile inside its fair comparison set

14.3%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 #168 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.2%
Percentile: 44%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

44% percentile inside its fair comparison set

13.2%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 #249 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.5%
Percentile: 21.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

21.3% percentile inside its fair comparison set

31.5%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 #64 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M tokens
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

77.2% percentile inside its fair comparison set

$0.2 /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 #50 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.1 /1M input tokens
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

83% percentile inside its fair comparison set

$0.1 /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 #70 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M output tokens
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

75.4% percentile inside its fair comparison set

$0.4 /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 #18 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 236 tokens/s
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

91.9% percentile inside its fair comparison set

236 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 #201 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.85s
Percentile: 4.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

4.8% percentile inside its fair comparison set

38.85sRaw 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 #172 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.85s
Percentile: 18.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

18.6% percentile inside its fair comparison set

38.85sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #174 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 7.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

7.5% percentile inside its fair comparison set

6Raw 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 #119 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #144. Votes: 47228. Organization: google. License: Proprietary.

63.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,376 - 1,383

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 #92 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 71.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing. Source rank: #115. Votes: 4187. Organization: google. License: Proprietary.

71.8% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,362 - 1,380

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 #126 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #151. Votes: 22616. Organization: google. License: Proprietary.

61.5% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,389

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 #120 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,351
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: exclude_ties. Source rank: #145. Votes: 33061. Organization: google. License: Proprietary.

63.4% percentile inside its fair comparison set

1,351Raw benchmark valueCI 1,346 - 1,356

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 #125 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts. Source rank: #151. Votes: 25066. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,386 - 1,395

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 #132 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 59.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts_english. Source rank: #158. Votes: 12545. Organization: google. License: Proprietary.

59.6% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,402

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 #117 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,369
Percentile: 64.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: instruction_following. Source rank: #143. Votes: 8103. Organization: google. License: Proprietary.

64.3% percentile inside its fair comparison set

1,369Raw benchmark valueCI 1,362 - 1,376

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 #115 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: longer_query. Source rank: #140. Votes: 11474. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,380 - 1,392

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 #122 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: multi_turn. Source rank: #147. Votes: 8193. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,366 - 1,381

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 #107 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 67.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #129. Votes: 47228. Organization: google. License: Proprietary.

67.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,376 - 1,382

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 #88 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing. Source rank: #108. Votes: 4187. Organization: google. License: Proprietary.

73.1% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,356 - 1,375

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #143. Votes: 22616. Organization: google. License: Proprietary.

63.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,377 - 1,386

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 #107 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 67.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: exclude_ties. Source rank: #129. Votes: 33061. Organization: google. License: Proprietary.

67.4% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,344 - 1,354

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 #110 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts. Source rank: #133. Votes: 25066. Organization: google. License: Proprietary.

66.5% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,372 - 1,381

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 #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts_english. Source rank: #141. Votes: 12545. Organization: google. License: Proprietary.

64.2% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,387

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 #104 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 68.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: instruction_following. Source rank: #127. Votes: 8103. Organization: google. License: Proprietary.

68.3% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,360 - 1,374

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 #107 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: longer_query. Source rank: #131. Votes: 6298. Organization: google. License: Proprietary.

65.1% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,366 - 1,381

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 #118 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: multi_turn. Source rank: #141. Votes: 8193. Organization: google. License: Proprietary.

63.8% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,359 - 1,373

Coding5 benchmarks40.8%

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 #225 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.3%
Percentile: 25.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

25.8% percentile inside its fair comparison set

2.3%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 #286 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 17.7%
Percentile: 22.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

22.6% percentile inside its fair comparison set

17.7%Raw benchmark value

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 #56 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.4%
Percentile: 38.9%
Last updated: recent
Eligibility: headline eligible

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

38.9% percentile inside its fair comparison set

71.4%Raw benchmark valueCI 69.2% - 73.6%

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 #140 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 56.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: coding. Source rank: #168. Votes: 9678. Organization: google. License: Proprietary.

56.6% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,391 - 1,404

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 #128 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: coding. Source rank: #153. Votes: 6001. Organization: google. License: Proprietary.

60.3% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,366 - 1,382

Reasoning / math / science7 benchmarks40.7%

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 #337 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.7%
Percentile: 9.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

9.5% percentile inside its fair comparison set

3.7%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 #258 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.4%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

31.3% percentile inside its fair comparison set

47.4%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 #177 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%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 #63 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.2%
Percentile: 30.3%
Last updated: recent
Eligibility: headline eligible

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

30.3% percentile inside its fair comparison set

70.2%Raw benchmark valueCI 65.7% - 74.7%

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 #65 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 79.1%
Percentile: 28.1%
Last updated: recent
Eligibility: headline eligible

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

28.1% percentile inside its fair comparison set

79.1%Raw benchmark valueCI 78.3% - 79.9%

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 #130 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 58.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: math. Source rank: #157. Votes: 2094. Organization: google. License: Proprietary.

58.9% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,352 - 1,377

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: math. Source rank: #144. Votes: 2878. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,384

Professional reasoning23 benchmarks56.6%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #45 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82%
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

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

51.1% percentile inside its fair comparison set

82%Raw benchmark valueCI 81.2% - 82.9%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #76 · Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.2%
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible

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

17.6% percentile inside its fair comparison set

66.2%Raw benchmark valueCI 64.4% - 68%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #40 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.2%
Percentile: 23.5%
Last updated: recent
Eligibility: headline eligible

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

23.5% percentile inside its fair comparison set

34.2%Raw benchmark valueCI 30.8% - 37.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #32 · Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.8%
Percentile: 38%
Last updated: recent
Eligibility: headline eligible

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

38% percentile inside its fair comparison set

75.8%Raw benchmark valueCI 72.2% - 79.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: expert. Source rank: #147. Votes: 2538. Organization: google. License: Proprietary.

56.4% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,375 - 1,399

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 #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 63.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #142. Votes: 9034. Organization: google. License: Proprietary.

63.5% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,371 - 1,385

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 #100 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,361
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #124. Votes: 5852. Organization: google. License: Proprietary.

69.3% percentile inside its fair comparison set

1,361Raw benchmark valueCI 1,353 - 1,369

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #105 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_legal_and_government. Source rank: #128. Votes: 3150. Organization: google. License: Proprietary.

65.1% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,389 - 1,410

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 #116 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #139. Votes: 7456. Organization: google. License: Proprietary.

64.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,395 - 1,409

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #128 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 58.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_mathematical. Source rank: #154. Votes: 2075. Organization: google. License: Proprietary.

58.8% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,357 - 1,383

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #114 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 61.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_medicine_and_healthcare. Source rank: #137. Votes: 1984. Organization: google. License: Proprietary.

61.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,388 - 1,416

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 #134 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_software_and_it_services. Source rank: #160. Votes: 16634. Organization: google. License: Proprietary.

59.1% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,394 - 1,405

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 #97 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 70.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #119. Votes: 7099. Organization: google. License: Proprietary.

70.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,371 - 1,386

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #104 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: expert. Source rank: #127. Votes: 2538. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,362 - 1,385

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 #110 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #132. Votes: 9034. Organization: google. License: Proprietary.

65.7% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,361 - 1,374

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 #100 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #122. Votes: 5852. Organization: google. License: Proprietary.

69.3% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,346 - 1,362

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 #104 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_legal_and_government. Source rank: #125. Votes: 3150. Organization: google. License: Proprietary.

65.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,383 - 1,404

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 #106 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 67.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #127. Votes: 7456. Organization: google. License: Proprietary.

67.5% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,388 - 1,402

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 62.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_mathematical. Source rank: #142. Votes: 2075. Organization: google. License: Proprietary.

62.3% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,364 - 1,389

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 #109 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_medicine_and_healthcare. Source rank: #131. Votes: 2520. Organization: google. License: Proprietary.

63.4% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,376 - 1,400

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_software_and_it_services. Source rank: #144. Votes: 16634. Organization: google. License: Proprietary.

63.1% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,390

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 #91 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #113. Votes: 7099. Organization: google. License: Proprietary.

72.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,367 - 1,381

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #41 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30.8%
Percentile: 11.1%
Last updated: recent
Eligibility: headline eligible

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

11.1% percentile inside its fair comparison set

30.8%Raw benchmark valueCI 24.7% - 36.9%

Search / tool use1 benchmark20.7%

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 #247 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.4%
Percentile: 20.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

20.7% percentile inside its fair comparison set

18.4%Raw benchmark value

Long context2 benchmarks42.2%

Long Context Reasoning

AA · Long context · Objective

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

Rank #148 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.3%
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

53.7% percentile inside its fair comparison set

31.3%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 #62 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.6%
Percentile: 30.7%
Last updated: recent
Eligibility: headline eligible

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

30.7% percentile inside its fair comparison set

57.6%Raw benchmark valueCI 55.7% - 59.5%

Vision understanding22 benchmarks36%

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 #91 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

33.3% percentile inside its fair comparison set

54%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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: overall. Source rank: #65. Votes: 36820. Organization: google. License: Proprietary.

52.3% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,181 - 1,196

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #16 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,189
Percentile: 42.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: captioning. Source rank: #15. Votes: 403. Organization: google. License: Proprietary.

42.3% percentile inside its fair comparison set

1,189Raw benchmark valueCI 1,158 - 1,219

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 #46 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 18.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing_vision. Source rank: #56. Votes: 1207. Organization: google. License: Proprietary.

18.2% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,168 - 1,208

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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,187
Percentile: 25.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: diagram. Source rank: #68. Votes: 2500. Organization: google. License: Proprietary.

25.7% percentile inside its fair comparison set

1,187Raw benchmark valueCI 1,174 - 1,200

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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: english. Source rank: #66. Votes: 17444. Organization: google. License: Proprietary.

52.3% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,179 - 1,198

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 #24 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 28.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: entity_recognition. Source rank: #26. Votes: 422. Organization: google. License: Proprietary.

28.1% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,157 - 1,218

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 #51 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,196
Percentile: 26.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: homework. Source rank: #65. Votes: 619. Organization: google. License: Proprietary.

26.5% percentile inside its fair comparison set

1,196Raw benchmark valueCI 1,175 - 1,218

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 #35 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 30.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: humor. Source rank: #45. Votes: 1431. Organization: google. License: Proprietary.

30.6% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,169 - 1,208

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 #52 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 27.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: ocr. Source rank: #66. Votes: 10707. Organization: google. License: Proprietary.

27.1% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,179 - 1,197

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 #46 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,199
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #59. Votes: 4767. Organization: google. License: Proprietary.

58.7% percentile inside its fair comparison set

1,199Raw benchmark valueCI 1,190 - 1,209

Vision Arena · Captioning · 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 #20 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,189
Percentile: 26.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: captioning. Source rank: #20. Votes: 403. Organization: google. License: Proprietary.

26.9% percentile inside its fair comparison set

1,189Raw benchmark valueCI 1,159 - 1,218

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 #42 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,201
Percentile: 25.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: creative_writing_vision. Source rank: #53. Votes: 316. Organization: google. License: Proprietary.

25.5% percentile inside its fair comparison set

1,201Raw benchmark valueCI 1,170 - 1,233

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 #47 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,200
Percentile: 34.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: diagram. Source rank: #60. Votes: 983. Organization: google. License: Proprietary.

34.3% percentile inside its fair comparison set

1,200Raw benchmark valueCI 1,181 - 1,218

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 #47 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,206
Percentile: 57.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #60. Votes: 2148. Organization: google. License: Proprietary.

57.8% percentile inside its fair comparison set

1,206Raw benchmark valueCI 1,193 - 1,220

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 #29 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 12.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: entity_recognition. Source rank: #32. Votes: 422. Organization: google. License: Proprietary.

12.5% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,158 - 1,218

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 #48 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,214
Percentile: 30.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: homework. Source rank: #60. Votes: 619. Organization: google. License: Proprietary.

30.9% percentile inside its fair comparison set

1,214Raw benchmark valueCI 1,192 - 1,236

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 #38 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 24.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: humor. Source rank: #50. Votes: 1431. Organization: google. License: Proprietary.

24.5% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,169 - 1,207

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 #45 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,204
Percentile: 37.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: ocr. Source rank: #57. Votes: 2799. Organization: google. License: Proprietary.

37.1% percentile inside its fair comparison set

1,204Raw benchmark valueCI 1,192 - 1,215

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 #35 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.4%
Percentile: 41.4%
Last updated: recent
Eligibility: headline eligible

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

41.4% percentile inside its fair comparison set

75.4%Raw benchmark valueCI 73.4% - 77.5%

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #16 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,202
Percentile: 53.1%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: creative_writing. Source rank: #17. Votes: 565. Organization: google. License: Proprietary.

53.1% percentile inside its fair comparison set

1,202Raw benchmark valueCI 1,177 - 1,226

Vision Arena · Creative Writing · 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 #16 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 53.1%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: creative_writing. Source rank: #17. Votes: 565. Organization: google. License: Proprietary.

53.1% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,196 - 1,244

Document understanding1 benchmark23.3%

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 #47 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.6%
Percentile: 23.3%
Last updated: recent
Eligibility: headline eligible

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

23.3% percentile inside its fair comparison set

57.6%Raw benchmark valueCI 55.6% - 59.5%

Multilingual16 benchmarks60.7%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #111 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 62.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #136. Votes: 2176. Organization: google. License: Proprietary.

62.7% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,394 - 1,420

Text Arena · French

AR · Multilingual · Human

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

Rank #108 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: french. Source rank: #130. Votes: 402. Organization: google. License: Proprietary.

50.5% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,365 - 1,425

Text Arena · German

AR · Multilingual · Human

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

Rank #86 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 64.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: german. Source rank: #106. Votes: 780. Organization: google. License: Proprietary.

64.1% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,363 - 1,406

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #68 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,359
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: japanese. Source rank: #87. Votes: 414. Organization: google. License: Proprietary.

67% percentile inside its fair comparison set

1,359Raw benchmark valueCI 1,330 - 1,388

Text Arena · Korean

AR · Multilingual · Human

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

Rank #66 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: korean. Source rank: #84. Votes: 696. Organization: google. License: Proprietary.

68.8% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,342 - 1,388

Text Arena · Russian

AR · Multilingual · Human

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

Rank #109 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: russian. Source rank: #132. Votes: 1844. Organization: google. License: Proprietary.

62.6% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,364 - 1,391

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #86 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: spanish. Source rank: #107. Votes: 1259. Organization: google. License: Proprietary.

60.3% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,375 - 1,410

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #106 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #128. Votes: 2176. Organization: google. License: Proprietary.

64.4% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,392 - 1,417

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 54.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: french. Source rank: #118. Votes: 402. Organization: google. License: Proprietary.

54.6% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,358 - 1,418

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #80 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: german. Source rank: #97. Votes: 780. Organization: google. License: Proprietary.

66.7% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,368 - 1,411

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,363
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: japanese. Source rank: #78. Votes: 414. Organization: google. License: Proprietary.

70% percentile inside its fair comparison set

1,363Raw benchmark valueCI 1,334 - 1,392

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,359
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: korean. Source rank: #87. Votes: 696. Organization: google. License: Proprietary.

65.9% percentile inside its fair comparison set

1,359Raw benchmark valueCI 1,336 - 1,382

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: russian. Source rank: #126. Votes: 3755. Organization: google. License: Proprietary.

64.7% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,363 - 1,382

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #85 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: spanish. Source rank: #100. Votes: 1259. Organization: google. License: Proprietary.

60.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,381 - 1,416

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #46 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 41.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #58. Votes: 405. Organization: google. License: Proprietary.

41.6% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,177 - 1,234

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #42 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,230
Percentile: 46.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #54. Votes: 405. Organization: google. License: Proprietary.

46.8% percentile inside its fair comparison set

1,230Raw benchmark valueCI 1,202 - 1,259

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

Artificial Analysis

Jun 20, 2026

source →

Model profile · Google

Gemini 2.5 Flash-Lite

Closed weightsmid · registry tag 2026 cheap

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 21.9%
Verified coverage: 21.9%
Spread: 87.1%
Last verified: Jun 20, 2026

40%bench fit

textvisiondocumentaudiocode13 aliases40 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 / text29 benchmarks57.1%

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 #280 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 7
Percentile: 29.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

29.4% percentile inside its fair comparison set

7Raw 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 #203 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.3%
Percentile: 32.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

32.2% percentile inside its fair comparison set

14.3%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 #168 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 13.2%
Percentile: 44%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

44% percentile inside its fair comparison set

13.2%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 #249 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.5%
Percentile: 21.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

21.3% percentile inside its fair comparison set

31.5%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 #64 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.2 /1M tokens
Percentile: 77.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mBlended0To3To1`.

77.2% percentile inside its fair comparison set

$0.2 /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 #50 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.1 /1M input tokens
Percentile: 83%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

83% percentile inside its fair comparison set

$0.1 /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 #70 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.4 /1M output tokens
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

75.4% percentile inside its fair comparison set

$0.4 /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 #18 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 236 tokens/s
Percentile: 91.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

91.9% percentile inside its fair comparison set

236 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 #201 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.85s
Percentile: 4.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

4.8% percentile inside its fair comparison set

38.85sRaw 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 #172 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.85s
Percentile: 18.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

18.6% percentile inside its fair comparison set

38.85sRaw benchmark value

Openness Index

AA · Chat / text · Combined

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

Rank #174 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6
Percentile: 7.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `opennessBreakdown.opennessIndex`.

7.5% percentile inside its fair comparison set

6Raw 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 #119 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 63.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #144. Votes: 47228. Organization: google. License: Proprietary.

63.7% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,376 - 1,383

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 #92 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 71.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing. Source rank: #115. Votes: 4187. Organization: google. License: Proprietary.

71.8% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,362 - 1,380

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 #126 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #151. Votes: 22616. Organization: google. License: Proprietary.

61.5% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,380 - 1,389

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 #120 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,351
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: exclude_ties. Source rank: #145. Votes: 33061. Organization: google. License: Proprietary.

63.4% percentile inside its fair comparison set

1,351Raw benchmark valueCI 1,346 - 1,356

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 #125 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts. Source rank: #151. Votes: 25066. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,386 - 1,395

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 #132 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 59.6%
Last updated: recent
Eligibility: headline eligible

59.6% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,391 - 1,402

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 #117 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,369
Percentile: 64.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: instruction_following. Source rank: #143. Votes: 8103. Organization: google. License: Proprietary.

64.3% percentile inside its fair comparison set

1,369Raw benchmark valueCI 1,362 - 1,376

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 #115 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: longer_query. Source rank: #140. Votes: 11474. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,380 - 1,392

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 #122 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: multi_turn. Source rank: #147. Votes: 8193. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,366 - 1,381

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 #107 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 67.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #129. Votes: 47228. Organization: google. License: Proprietary.

67.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,376 - 1,382

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 #88 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 73.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing. Source rank: #108. Votes: 4187. Organization: google. License: Proprietary.

73.1% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,356 - 1,375

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #143. Votes: 22616. Organization: google. License: Proprietary.

63.1% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,377 - 1,386

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 #107 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,349
Percentile: 67.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: exclude_ties. Source rank: #129. Votes: 33061. Organization: google. License: Proprietary.

67.4% percentile inside its fair comparison set

1,349Raw benchmark valueCI 1,344 - 1,354

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 #110 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 66.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: hard_prompts. Source rank: #133. Votes: 25066. Organization: google. License: Proprietary.

66.5% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,372 - 1,381

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 #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 64.2%
Last updated: recent
Eligibility: headline eligible

64.2% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,375 - 1,387

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 #104 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 68.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: instruction_following. Source rank: #127. Votes: 8103. Organization: google. License: Proprietary.

68.3% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,360 - 1,374

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 #107 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: longer_query. Source rank: #131. Votes: 6298. Organization: google. License: Proprietary.

65.1% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,366 - 1,381

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 #118 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,366
Percentile: 63.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: multi_turn. Source rank: #141. Votes: 8193. Organization: google. License: Proprietary.

63.8% percentile inside its fair comparison set

1,366Raw benchmark valueCI 1,359 - 1,373

Coding5 benchmarks40.8%

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 #225 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 2.3%
Percentile: 25.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

25.8% percentile inside its fair comparison set

2.3%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 #286 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 17.7%
Percentile: 22.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

22.6% percentile inside its fair comparison set

17.7%Raw benchmark value

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 #56 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 71.4%
Percentile: 38.9%
Last updated: recent
Eligibility: headline eligible

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

38.9% percentile inside its fair comparison set

71.4%Raw benchmark valueCI 69.2% - 73.6%

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 #140 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 56.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: coding. Source rank: #168. Votes: 9678. Organization: google. License: Proprietary.

56.6% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,391 - 1,404

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 #128 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: coding. Source rank: #153. Votes: 6001. Organization: google. License: Proprietary.

60.3% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,366 - 1,382

Reasoning / math / science7 benchmarks40.7%

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 #337 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 3.7%
Percentile: 9.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

9.5% percentile inside its fair comparison set

3.7%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 #258 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.4%
Percentile: 31.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

31.3% percentile inside its fair comparison set

47.4%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 #177 · Source label: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0%
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

65.2% percentile inside its fair comparison set

0%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 #63 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.2%
Percentile: 30.3%
Last updated: recent
Eligibility: headline eligible

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

30.3% percentile inside its fair comparison set

70.2%Raw benchmark valueCI 65.7% - 74.7%

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 #65 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 79.1%
Percentile: 28.1%
Last updated: recent
Eligibility: headline eligible

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

28.1% percentile inside its fair comparison set

79.1%Raw benchmark valueCI 78.3% - 79.9%

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 #130 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 58.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: math. Source rank: #157. Votes: 2094. Organization: google. License: Proprietary.

58.9% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,352 - 1,377

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: math. Source rank: #144. Votes: 2878. Organization: google. License: Proprietary.

61.8% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,363 - 1,384

Professional reasoning23 benchmarks56.6%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #45 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 82%
Percentile: 51.1%
Last updated: recent
Eligibility: headline eligible

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

51.1% percentile inside its fair comparison set

82%Raw benchmark valueCI 81.2% - 82.9%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #76 · Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.2%
Percentile: 17.6%
Last updated: recent
Eligibility: headline eligible

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

17.6% percentile inside its fair comparison set

66.2%Raw benchmark valueCI 64.4% - 68%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #40 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.2%
Percentile: 23.5%
Last updated: recent
Eligibility: headline eligible

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

23.5% percentile inside its fair comparison set

34.2%Raw benchmark valueCI 30.8% - 37.6%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #32 · Source label: google/gemini-2.5-flash-lite-preview-09-2025

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.8%
Percentile: 38%
Last updated: recent
Eligibility: headline eligible

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

38% percentile inside its fair comparison set

75.8%Raw benchmark valueCI 72.2% - 79.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 56.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: expert. Source rank: #147. Votes: 2538. Organization: google. License: Proprietary.

56.4% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,375 - 1,399

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 #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 63.5%
Last updated: recent
Eligibility: headline eligible

63.5% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,371 - 1,385

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 #100 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,361
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

69.3% percentile inside its fair comparison set

1,361Raw benchmark valueCI 1,353 - 1,369

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #105 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

65.1% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,389 - 1,410

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 #116 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

64.4% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,395 - 1,409

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #128 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 58.8%
Last updated: recent
Eligibility: headline eligible

58.8% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,357 - 1,383

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #114 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 61.7%
Last updated: recent
Eligibility: headline eligible

61.7% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,388 - 1,416

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 #134 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 59.1%
Last updated: recent
Eligibility: headline eligible

59.1% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,394 - 1,405

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 #97 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 70.4%
Last updated: recent
Eligibility: headline eligible

70.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,371 - 1,386

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #104 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: expert. Source rank: #127. Votes: 2538. Organization: google. License: Proprietary.

62.5% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,362 - 1,385

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 #110 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,368
Percentile: 65.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_business_and_management_and_financial_operations. Source rank: #132. Votes: 9034. Organization: google. License: Proprietary.

65.7% percentile inside its fair comparison set

1,368Raw benchmark valueCI 1,361 - 1,374

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 #100 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 69.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_entertainment_and_sports_and_media. Source rank: #122. Votes: 5852. Organization: google. License: Proprietary.

69.3% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,346 - 1,362

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 #104 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,393
Percentile: 65.4%
Last updated: recent
Eligibility: headline eligible

65.4% percentile inside its fair comparison set

1,393Raw benchmark valueCI 1,383 - 1,404

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 #106 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 67.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: industry_life_and_physical_and_social_science. Source rank: #127. Votes: 7456. Organization: google. License: Proprietary.

67.5% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,388 - 1,402

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #117 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 62.3%
Last updated: recent
Eligibility: headline eligible

62.3% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,364 - 1,389

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 #109 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

63.4% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,376 - 1,400

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 #121 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 63.1%
Last updated: recent
Eligibility: headline eligible

63.1% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,390

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 #91 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 72.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: industry_writing_and_literature_and_language. Source rank: #113. Votes: 7099. Organization: google. License: Proprietary.

72.2% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,367 - 1,381

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #41 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 30.8%
Percentile: 11.1%
Last updated: recent
Eligibility: headline eligible

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

11.1% percentile inside its fair comparison set

30.8%Raw benchmark valueCI 24.7% - 36.9%

Search / tool use1 benchmark20.7%

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 #247 · Source label: Gemini 2.5 Flash-Lite (Reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.4%
Percentile: 20.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

20.7% percentile inside its fair comparison set

18.4%Raw benchmark value

Long context2 benchmarks42.2%

Long Context Reasoning

AA · Long context · Objective

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

Rank #148 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 31.3%
Percentile: 53.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

53.7% percentile inside its fair comparison set

31.3%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 #62 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.6%
Percentile: 30.7%
Last updated: recent
Eligibility: headline eligible

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

30.7% percentile inside its fair comparison set

57.6%Raw benchmark valueCI 55.7% - 59.5%

Vision understanding22 benchmarks36%

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 #91 · Source label: Gemini 2.5 Flash-Lite (Non-reasoning)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54%
Percentile: 33.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

33.3% percentile inside its fair comparison set

54%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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: overall. Source rank: #65. Votes: 36820. Organization: google. License: Proprietary.

52.3% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,181 - 1,196

Vision Arena · Captioning

AR · Vision understanding · Human

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

Rank #16 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,189
Percentile: 42.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: captioning. Source rank: #15. Votes: 403. Organization: google. License: Proprietary.

42.3% percentile inside its fair comparison set

1,189Raw benchmark valueCI 1,158 - 1,219

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 #46 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 18.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: creative_writing_vision. Source rank: #56. Votes: 1207. Organization: google. License: Proprietary.

18.2% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,168 - 1,208

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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,187
Percentile: 25.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: diagram. Source rank: #68. Votes: 2500. Organization: google. License: Proprietary.

25.7% percentile inside its fair comparison set

1,187Raw benchmark valueCI 1,174 - 1,200

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 #53 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: english. Source rank: #66. Votes: 17444. Organization: google. License: Proprietary.

52.3% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,179 - 1,198

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 #24 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 28.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: entity_recognition. Source rank: #26. Votes: 422. Organization: google. License: Proprietary.

28.1% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,157 - 1,218

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 #51 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,196
Percentile: 26.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: homework. Source rank: #65. Votes: 619. Organization: google. License: Proprietary.

26.5% percentile inside its fair comparison set

1,196Raw benchmark valueCI 1,175 - 1,218

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 #35 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 30.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: humor. Source rank: #45. Votes: 1431. Organization: google. License: Proprietary.

30.6% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,169 - 1,208

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 #52 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 27.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: ocr. Source rank: #66. Votes: 10707. Organization: google. License: Proprietary.

27.1% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,179 - 1,197

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 #46 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,199
Percentile: 58.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: overall. Source rank: #59. Votes: 4767. Organization: google. License: Proprietary.

58.7% percentile inside its fair comparison set

1,199Raw benchmark valueCI 1,190 - 1,209

Vision Arena · Captioning · 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 #20 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,189
Percentile: 26.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: captioning. Source rank: #20. Votes: 403. Organization: google. License: Proprietary.

26.9% percentile inside its fair comparison set

1,189Raw benchmark valueCI 1,159 - 1,218

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 #42 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,201
Percentile: 25.5%
Last updated: recent
Eligibility: headline eligible

25.5% percentile inside its fair comparison set

1,201Raw benchmark valueCI 1,170 - 1,233

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 #47 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,200
Percentile: 34.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: diagram. Source rank: #60. Votes: 983. Organization: google. License: Proprietary.

34.3% percentile inside its fair comparison set

1,200Raw benchmark valueCI 1,181 - 1,218

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 #47 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,206
Percentile: 57.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: english. Source rank: #60. Votes: 2148. Organization: google. License: Proprietary.

57.8% percentile inside its fair comparison set

1,206Raw benchmark valueCI 1,193 - 1,220

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 #29 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 12.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: entity_recognition. Source rank: #32. Votes: 422. Organization: google. License: Proprietary.

12.5% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,158 - 1,218

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 #48 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,214
Percentile: 30.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: homework. Source rank: #60. Votes: 619. Organization: google. License: Proprietary.

30.9% percentile inside its fair comparison set

1,214Raw benchmark valueCI 1,192 - 1,236

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 #38 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,188
Percentile: 24.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: humor. Source rank: #50. Votes: 1431. Organization: google. License: Proprietary.

24.5% percentile inside its fair comparison set

1,188Raw benchmark valueCI 1,169 - 1,207

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 #45 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,204
Percentile: 37.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: ocr. Source rank: #57. Votes: 2799. Organization: google. License: Proprietary.

37.1% percentile inside its fair comparison set

1,204Raw benchmark valueCI 1,192 - 1,215

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 #35 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 75.4%
Percentile: 41.4%
Last updated: recent
Eligibility: headline eligible

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

41.4% percentile inside its fair comparison set

75.4%Raw benchmark valueCI 73.4% - 77.5%

Vision Arena · Creative Writing

AR · Vision understanding · Human

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

Rank #16 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,202
Percentile: 53.1%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: creative_writing. Source rank: #17. Votes: 565. Organization: google. License: Proprietary.

53.1% percentile inside its fair comparison set

1,202Raw benchmark valueCI 1,177 - 1,226

Vision Arena · Creative Writing · 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 #16 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,220
Percentile: 53.1%
Last updated: archived
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: creative_writing. Source rank: #17. Votes: 565. Organization: google. License: Proprietary.

53.1% percentile inside its fair comparison set

1,220Raw benchmark valueCI 1,196 - 1,244

Document understanding1 benchmark23.3%

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 #47 · Source label: google/gemini-2.5-flash-lite-preview-09-2025-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 57.6%
Percentile: 23.3%
Last updated: recent
Eligibility: headline eligible

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

23.3% percentile inside its fair comparison set

57.6%Raw benchmark valueCI 55.6% - 59.5%

Multilingual16 benchmarks60.7%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #111 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,407
Percentile: 62.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #136. Votes: 2176. Organization: google. License: Proprietary.

62.7% percentile inside its fair comparison set

1,407Raw benchmark valueCI 1,394 - 1,420

Text Arena · French

AR · Multilingual · Human

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

Rank #108 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 50.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: french. Source rank: #130. Votes: 402. Organization: google. License: Proprietary.

50.5% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,365 - 1,425

Text Arena · German

AR · Multilingual · Human

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

Rank #86 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 64.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: german. Source rank: #106. Votes: 780. Organization: google. License: Proprietary.

64.1% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,363 - 1,406

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #68 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,359
Percentile: 67%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: japanese. Source rank: #87. Votes: 414. Organization: google. License: Proprietary.

67% percentile inside its fair comparison set

1,359Raw benchmark valueCI 1,330 - 1,388

Text Arena · Korean

AR · Multilingual · Human

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

Rank #66 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: korean. Source rank: #84. Votes: 696. Organization: google. License: Proprietary.

68.8% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,342 - 1,388

Text Arena · Russian

AR · Multilingual · Human

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

Rank #109 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: russian. Source rank: #132. Votes: 1844. Organization: google. License: Proprietary.

62.6% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,364 - 1,391

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #86 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 60.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: spanish. Source rank: #107. Votes: 1259. Organization: google. License: Proprietary.

60.3% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,375 - 1,410

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #106 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #128. Votes: 2176. Organization: google. License: Proprietary.

64.4% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,392 - 1,417

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #99 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 54.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: french. Source rank: #118. Votes: 402. Organization: google. License: Proprietary.

54.6% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,358 - 1,418

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #80 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: german. Source rank: #97. Votes: 780. Organization: google. License: Proprietary.

66.7% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,368 - 1,411

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #62 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,363
Percentile: 70%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: japanese. Source rank: #78. Votes: 414. Organization: google. License: Proprietary.

70% percentile inside its fair comparison set

1,363Raw benchmark valueCI 1,334 - 1,392

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #72 · Source label: gemini-2.5-flash-lite-preview-06-17-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,359
Percentile: 65.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-06-17-thinking`. Category: korean. Source rank: #87. Votes: 696. Organization: google. License: Proprietary.

65.9% percentile inside its fair comparison set

1,359Raw benchmark valueCI 1,336 - 1,382

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #103 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: russian. Source rank: #126. Votes: 3755. Organization: google. License: Proprietary.

64.7% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,363 - 1,382

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #85 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 60.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: spanish. Source rank: #100. Votes: 1259. Organization: google. License: Proprietary.

60.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,381 - 1,416

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #46 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,205
Percentile: 41.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #58. Votes: 405. Organization: google. License: Proprietary.

41.6% percentile inside its fair comparison set

1,205Raw benchmark valueCI 1,177 - 1,234

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #42 · Source label: gemini-2.5-flash-lite-preview-09-2025-no-thinking

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,230
Percentile: 46.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-2.5-flash-lite-preview-09-2025-no-thinking`. Category: chinese. Source rank: #54. Votes: 405. Organization: google. License: Proprietary.

46.8% percentile inside its fair comparison set

1,230Raw benchmark valueCI 1,202 - 1,259