Model profile · Unknown

muse-spark

Unknown weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 19.9%
Verified coverage: 19.9%
Spread: n/a
Last verified: Jun 20, 2026

textcodevisiondocument2 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 / text22 benchmarks95.7%

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 #7 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.5% percentile inside its fair comparison set

43Raw 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 #10 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.6%
Percentile: 97%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97% percentile inside its fair comparison set

44.6%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 #74 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26.8%
Percentile: 75.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

75.5% percentile inside its fair comparison set

26.8%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 #11 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.9%
Percentile: 96.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

96.8% percentile inside its fair comparison set

75.9%Raw 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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 99.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 13607. Organization: meta. License: Proprietary.

99.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,481 - 1,493

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing. Source rank: #11. Votes: 1955. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,449 - 1,477

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 99.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 6479. Organization: meta. License: Proprietary.

99.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,487 - 1,503

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: exclude_ties. Source rank: #8. Votes: 10312. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts. Source rank: #11. Votes: 8739. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,497 - 1,511

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 97.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts_english. Source rank: #10. Votes: 4351. Organization: meta. License: Proprietary.

97.8% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,497 - 1,516

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 #17

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 95.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: instruction_following. Source rank: #24. Votes: 4489. Organization: meta. License: Proprietary.

95.1% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,454 - 1,472

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 #22

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 93.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: longer_query. Source rank: #29. Votes: 5275. Organization: meta. License: Proprietary.

93.1% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,464 - 1,482

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: multi_turn. Source rank: #12. Votes: 2168. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,477 - 1,504

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 98.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #10. Votes: 13607. Organization: meta. License: Proprietary.

98.2% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,466 - 1,478

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing. Source rank: #12. Votes: 1955. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,444 - 1,472

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #8. Votes: 6479. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,487

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 97.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: exclude_ties. Source rank: #11. Votes: 10312. Organization: meta. License: Proprietary.

97.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,469 - 1,484

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 #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts. Source rank: #22. Votes: 8739. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,466 - 1,480

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 #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts_english. Source rank: #21. Votes: 4351. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,466 - 1,485

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 #22

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 93.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: instruction_following. Source rank: #29. Votes: 4489. Organization: meta. License: Proprietary.

93.5% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,432 - 1,451

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 #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: longer_query. Source rank: #34. Votes: 5275. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,457

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 #12

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: multi_turn. Source rank: #15. Votes: 2168. Organization: meta. License: Proprietary.

96.6% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,462 - 1,489

Coding8 benchmarks79.4%

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 #10 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.5%
Percentile: 97%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

97% percentile inside its fair comparison set

45.5%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 #4 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.5%
Percentile: 99.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

99.2% percentile inside its fair comparison set

51.5%Raw benchmark value

Coding Index

AA · Coding · Combined

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

Rank #13 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 59
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

84% percentile inside its fair comparison set

59Raw benchmark value

Agentic Index

AA · Coding · Combined

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

Rank #17 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29
Percentile: 65.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

65.2% percentile inside its fair comparison set

29Raw benchmark value

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #22 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 61.1%
Last updated: recent
Eligibility: benchmark_derived_model

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

61.1% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 70.6% - 78.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #31 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.7%
Percentile: 38.8%
Last updated: recent
Eligibility: benchmark_derived_model

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

38.8% percentile inside its fair comparison set

19.7%Raw benchmark valueCI 11.9% - 27.4%

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: coding. Source rank: #13. Votes: 3781. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,515 - 1,535

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 #24

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 92.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: coding. Source rank: #30. Votes: 3781. Organization: meta. License: Proprietary.

92.8% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,468 - 1,488

Reasoning / math / science8 benchmarks86.4%

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 #5 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.9%
Percentile: 98.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

98.9% percentile inside its fair comparison set

39.9%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 #14 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 88.4%
Percentile: 96.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

96.5% percentile inside its fair comparison set

88.4%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 #9 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.3%
Percentile: 97.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

97.4% percentile inside its fair comparison set

11.3%Raw benchmark value

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #20 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 17%
Percentile: 45.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Meta.

45.7% percentile inside its fair comparison set

17%Raw benchmark valueCI 9.6% - 24.4%

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 #13 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 86.5%
Last updated: recent
Eligibility: benchmark_derived_model

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

86.5% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 86.6% - 92.7%

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 #17 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 82%
Last updated: recent
Eligibility: benchmark_derived_model

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

82% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.7% - 88%

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 #25

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 92.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: math. Source rank: #30. Votes: 862. Organization: meta. License: Proprietary.

92.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,443 - 1,483

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 #26

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 92%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: math. Source rank: #33. Votes: 862. Organization: meta. License: Proprietary.

92% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,432 - 1,472

Professional reasoning23 benchmarks92.7%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #21 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,152
Percentile: 56.5%
Last updated: recent
Eligibility: benchmark_derived_model

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

56.5% percentile inside its fair comparison set

1,152Raw benchmark value

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #21 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.2%
Percentile: 77.8%
Last updated: recent
Eligibility: benchmark_derived_model

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

77.8% percentile inside its fair comparison set

84.2%Raw benchmark valueCI 83.4% - 85%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #1 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.7%
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

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

100% percentile inside its fair comparison set

77.7%Raw benchmark valueCI 76.1% - 79.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #9 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.3%
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model

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

84.3% percentile inside its fair comparison set

51.3%Raw benchmark valueCI 46.9% - 55.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #6 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model

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

90% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 82.3% - 89.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #24

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: expert. Source rank: #30. Votes: 1271. Organization: meta. License: Proprietary.

91.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,470 - 1,504

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 98.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_business_and_management_and_financial_operations. Source rank: #8. Votes: 2736. Organization: meta. License: Proprietary.

98.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,476 - 1,500

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_entertainment_and_sports_and_media. Source rank: #8. Votes: 2518. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,448 - 1,473

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_legal_and_government. Source rank: #6. Votes: 963. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,484 - 1,524

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_life_and_physical_and_social_science. Source rank: #11. Votes: 2268. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,485 - 1,511

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 91.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_mathematical. Source rank: #33. Votes: 812. Organization: meta. License: Proprietary.

91.6% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,449 - 1,491

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_medicine_and_healthcare. Source rank: #7. Votes: 967. Organization: meta. License: Proprietary.

98.6% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,486 - 1,526

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_software_and_it_services. Source rank: #8. Votes: 5323. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,510 - 1,527

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 #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 95.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_writing_and_literature_and_language. Source rank: #21. Votes: 3138. Organization: meta. License: Proprietary.

95.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,447 - 1,469

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #35

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 87.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: expert. Source rank: #43. Votes: 1271. Organization: meta. License: Proprietary.

87.6% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,437 - 1,471

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 #11

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 96.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_business_and_management_and_financial_operations. Source rank: #14. Votes: 2736. Organization: meta. License: Proprietary.

96.9% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,449 - 1,473

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_entertainment_and_sports_and_media. Source rank: #12. Votes: 2518. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,436 - 1,460

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 #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_legal_and_government. Source rank: #6. Votes: 963. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,470 - 1,509

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 #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 96%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_life_and_physical_and_social_science. Source rank: #18. Votes: 2268. Organization: meta. License: Proprietary.

96% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,465 - 1,491

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #31

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 90.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_mathematical. Source rank: #38. Votes: 812. Organization: meta. License: Proprietary.

90.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,432 - 1,474

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_medicine_and_healthcare. Source rank: #10. Votes: 967. Organization: meta. License: Proprietary.

97.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,464 - 1,503

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 #17

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 95.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_software_and_it_services. Source rank: #20. Votes: 5323. Organization: meta. License: Proprietary.

95.1% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,475 - 1,492

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 #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 95.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_writing_and_literature_and_language. Source rank: #20. Votes: 3138. Organization: meta. License: Proprietary.

95.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,439 - 1,461

Search / tool use1 benchmark88.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #37 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 91.5%
Percentile: 88.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

88.3% percentile inside its fair comparison set

91.5%Raw benchmark value

Long context2 benchmarks87.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #6 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.7%
Percentile: 98.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

98.4% percentile inside its fair comparison set

69.7%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 #22 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.1%
Percentile: 76.1%
Last updated: recent
Eligibility: benchmark_derived_model

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

76.1% percentile inside its fair comparison set

65.1%Raw benchmark valueCI 63.3% - 66.9%

Vision understanding16 benchmarks93.3%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #2 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.5%
Percentile: 99.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

99.3% percentile inside its fair comparison set

80.5%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,295
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 5613. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,295Raw benchmark valueCI 1,285 - 1,304

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,306
Percentile: 94.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing_vision. Source rank: #4. Votes: 338. Organization: meta. License: Proprietary.

94.5% percentile inside its fair comparison set

1,306Raw benchmark valueCI 1,273 - 1,340

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,312
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: diagram. Source rank: #10. Votes: 1526. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,312Raw benchmark valueCI 1,296 - 1,327

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 2336. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,275 - 1,303

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: homework. Source rank: #18. Votes: 940. Organization: meta. License: Proprietary.

80.9% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,278 - 1,317

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 #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: humor. Source rank: #1. Votes: 230. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,283 - 1,364

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 92.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: ocr. Source rank: #8. Votes: 4040. Organization: meta. License: Proprietary.

92.9% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,293 - 1,313

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,307
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 5613. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,307Raw benchmark valueCI 1,298 - 1,317

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 94.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing_vision. Source rank: #4. Votes: 338. Organization: meta. License: Proprietary.

94.5% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,296 - 1,363

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: diagram. Source rank: #12. Votes: 1526. Organization: meta. License: Proprietary.

90% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,294 - 1,326

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 2336. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,289 - 1,317

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 #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,298
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: homework. Source rank: #18. Votes: 940. Organization: meta. License: Proprietary.

80.9% percentile inside its fair comparison set

1,298Raw benchmark valueCI 1,279 - 1,318

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 #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: humor. Source rank: #1. Votes: 230. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,302 - 1,383

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,309
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: ocr. Source rank: #9. Votes: 4040. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,309Raw benchmark valueCI 1,298 - 1,319

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 #8 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.4%
Percentile: 87.9%
Last updated: recent
Eligibility: benchmark_derived_model

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

87.9% percentile inside its fair comparison set

87.4%Raw benchmark valueCI 85.8% - 89%

Document understanding2 benchmarks60.4%

Document Arena

AR · Document understanding · Human

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

Rank #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 66.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #12. Votes: 1081. Organization: meta. License: Proprietary.

66.7% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,448 - 1,485

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #12

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 54.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #15. Votes: 1081. Organization: meta. License: Proprietary.

54.2% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,424 - 1,460

Multilingual14 benchmarks97.3%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 96.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #14. Votes: 852. Organization: meta. License: Proprietary.

96.9% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,502 - 1,545

Text Arena · French

AR · Multilingual · Human

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

Rank #2

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: french. Source rank: #2. Votes: 468. Organization: meta. License: Proprietary.

99.5% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,495 - 1,554

Text Arena · German

AR · Multilingual · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: german. Source rank: #4. Votes: 234. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,466 - 1,546

Text Arena · Korean

AR · Multilingual · Human

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

Rank #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: korean. Source rank: #1. Votes: 254. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,440 - 1,518

Text Arena · Russian

AR · Multilingual · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 95.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: russian. Source rank: #19. Votes: 1482. Organization: meta. License: Proprietary.

95.5% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,464 - 1,496

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: spanish. Source rank: #6. Votes: 501. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,455 - 1,510

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 95.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #19. Votes: 852. Organization: meta. License: Proprietary.

95.6% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,484 - 1,527

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: french. Source rank: #7. Votes: 468. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,471 - 1,529

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 97.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: german. Source rank: #6. Votes: 234. Organization: meta. License: Proprietary.

97.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,452 - 1,531

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: korean. Source rank: #4. Votes: 254. Organization: meta. License: Proprietary.

98.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,425 - 1,503

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #13

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 95.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: russian. Source rank: #17. Votes: 1482. Organization: meta. License: Proprietary.

95.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,449 - 1,481

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: spanish. Source rank: #6. Votes: 501. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,447 - 1,501

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #7. Votes: 447. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,310 - 1,374

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #7. Votes: 447. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,323 - 1,386

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

Model profile · Unknown

muse-spark

Unknown weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 19.9%
Verified coverage: 19.9%
Spread: n/a
Last verified: Jun 20, 2026

textcodevisiondocument2 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 / text22 benchmarks95.7%

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 #7 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 43
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.5% percentile inside its fair comparison set

43Raw 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 #10 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.6%
Percentile: 97%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

97% percentile inside its fair comparison set

44.6%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 #74 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 26.8%
Percentile: 75.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

75.5% percentile inside its fair comparison set

26.8%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 #11 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 75.9%
Percentile: 96.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `ifbench`.

96.8% percentile inside its fair comparison set

75.9%Raw 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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 99.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 13607. Organization: meta. License: Proprietary.

99.1% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,481 - 1,493

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing. Source rank: #11. Votes: 1955. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,449 - 1,477

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 99.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 6479. Organization: meta. License: Proprietary.

99.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,487 - 1,503

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: exclude_ties. Source rank: #8. Votes: 10312. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,507

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts. Source rank: #11. Votes: 8739. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,497 - 1,511

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 97.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts_english. Source rank: #10. Votes: 4351. Organization: meta. License: Proprietary.

97.8% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,497 - 1,516

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 #17

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 95.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: instruction_following. Source rank: #24. Votes: 4489. Organization: meta. License: Proprietary.

95.1% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,454 - 1,472

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 #22

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 93.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: longer_query. Source rank: #29. Votes: 5275. Organization: meta. License: Proprietary.

93.1% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,464 - 1,482

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: multi_turn. Source rank: #12. Votes: 2168. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,477 - 1,504

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 98.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #10. Votes: 13607. Organization: meta. License: Proprietary.

98.2% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,466 - 1,478

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing. Source rank: #12. Votes: 1955. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,444 - 1,472

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #8. Votes: 6479. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,471 - 1,487

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,477
Percentile: 97.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: exclude_ties. Source rank: #11. Votes: 10312. Organization: meta. License: Proprietary.

97.8% percentile inside its fair comparison set

1,477Raw benchmark valueCI 1,469 - 1,484

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 #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts. Source rank: #22. Votes: 8739. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,466 - 1,480

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 #18

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: hard_prompts_english. Source rank: #21. Votes: 4351. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,466 - 1,485

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 #22

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 93.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: instruction_following. Source rank: #29. Votes: 4489. Organization: meta. License: Proprietary.

93.5% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,432 - 1,451

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 #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: longer_query. Source rank: #34. Votes: 5275. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,440 - 1,457

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 #12

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,475
Percentile: 96.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: multi_turn. Source rank: #15. Votes: 2168. Organization: meta. License: Proprietary.

96.6% percentile inside its fair comparison set

1,475Raw benchmark valueCI 1,462 - 1,489

Coding8 benchmarks79.4%

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 #10 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 45.5%
Percentile: 97%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

97% percentile inside its fair comparison set

45.5%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 #4 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 51.5%
Percentile: 99.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `scicode`.

99.2% percentile inside its fair comparison set

51.5%Raw benchmark value

Coding Index

AA · Coding · Combined

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

Rank #13 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 59
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `codingIndex`.

84% percentile inside its fair comparison set

59Raw benchmark value

Agentic Index

AA · Coding · Combined

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

Rank #17 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 29
Percentile: 65.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `agenticIndex`.

65.2% percentile inside its fair comparison set

29Raw benchmark value

SWE-bench Verified

VALS-AI · Coding · Objective

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

Rank #22 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 61.1%
Last updated: recent
Eligibility: benchmark_derived_model

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

61.1% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 70.6% - 78.2%

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

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

Rank #31 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.7%
Percentile: 38.8%
Last updated: recent
Eligibility: benchmark_derived_model

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

38.8% percentile inside its fair comparison set

19.7%Raw benchmark valueCI 11.9% - 27.4%

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: coding. Source rank: #13. Votes: 3781. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,515 - 1,535

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 #24

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 92.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: coding. Source rank: #30. Votes: 3781. Organization: meta. License: Proprietary.

92.8% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,468 - 1,488

Reasoning / math / science8 benchmarks86.4%

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 #5 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39.9%
Percentile: 98.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `hle`.

98.9% percentile inside its fair comparison set

39.9%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 #14 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 88.4%
Percentile: 96.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `gpqa`.

96.5% percentile inside its fair comparison set

88.4%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 #9 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.3%
Percentile: 97.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `critpt`.

97.4% percentile inside its fair comparison set

11.3%Raw benchmark value

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #20 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 17%
Percentile: 45.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Meta.

45.7% percentile inside its fair comparison set

17%Raw benchmark valueCI 9.6% - 24.4%

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 #13 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.6%
Percentile: 86.5%
Last updated: recent
Eligibility: benchmark_derived_model

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

86.5% percentile inside its fair comparison set

89.6%Raw benchmark valueCI 86.6% - 92.7%

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 #17 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 82%
Last updated: recent
Eligibility: benchmark_derived_model

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

82% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.7% - 88%

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 #25

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,463
Percentile: 92.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: math. Source rank: #30. Votes: 862. Organization: meta. License: Proprietary.

92.4% percentile inside its fair comparison set

1,463Raw benchmark valueCI 1,443 - 1,483

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 #26

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,452
Percentile: 92%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: math. Source rank: #33. Votes: 862. Organization: meta. License: Proprietary.

92% percentile inside its fair comparison set

1,452Raw benchmark valueCI 1,432 - 1,472

Professional reasoning23 benchmarks92.7%

GDPval-AA

AA · Professional reasoning · Rubric

Agentic performance on economically valuable work tasks.

Rank #21 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 1,152
Percentile: 56.5%
Last updated: recent
Eligibility: benchmark_derived_model

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

56.5% percentile inside its fair comparison set

1,152Raw benchmark value

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #21 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.2%
Percentile: 77.8%
Last updated: recent
Eligibility: benchmark_derived_model

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

77.8% percentile inside its fair comparison set

84.2%Raw benchmark valueCI 83.4% - 85%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #1 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.7%
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

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

100% percentile inside its fair comparison set

77.7%Raw benchmark valueCI 76.1% - 79.3%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #9 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51.3%
Percentile: 84.3%
Last updated: recent
Eligibility: benchmark_derived_model

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

84.3% percentile inside its fair comparison set

51.3%Raw benchmark valueCI 46.9% - 55.7%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #6 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 85.9%
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model

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

90% percentile inside its fair comparison set

85.9%Raw benchmark valueCI 82.3% - 89.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #24

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 91.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: expert. Source rank: #30. Votes: 1271. Organization: meta. License: Proprietary.

91.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,470 - 1,504

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 98.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_business_and_management_and_financial_operations. Source rank: #8. Votes: 2736. Organization: meta. License: Proprietary.

98.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,476 - 1,500

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_entertainment_and_sports_and_media. Source rank: #8. Votes: 2518. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,448 - 1,473

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_legal_and_government. Source rank: #6. Votes: 963. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,484 - 1,524

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 #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_life_and_physical_and_social_science. Source rank: #11. Votes: 2268. Organization: meta. License: Proprietary.

97.5% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,485 - 1,511

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #27

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,470
Percentile: 91.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_mathematical. Source rank: #33. Votes: 812. Organization: meta. License: Proprietary.

91.6% percentile inside its fair comparison set

1,470Raw benchmark valueCI 1,449 - 1,491

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_medicine_and_healthcare. Source rank: #7. Votes: 967. Organization: meta. License: Proprietary.

98.6% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,486 - 1,526

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 98.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_software_and_it_services. Source rank: #8. Votes: 5323. Organization: meta. License: Proprietary.

98.5% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,510 - 1,527

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 #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,458
Percentile: 95.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_writing_and_literature_and_language. Source rank: #21. Votes: 3138. Organization: meta. License: Proprietary.

95.4% percentile inside its fair comparison set

1,458Raw benchmark valueCI 1,447 - 1,469

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #35

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,454
Percentile: 87.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: expert. Source rank: #43. Votes: 1271. Organization: meta. License: Proprietary.

87.6% percentile inside its fair comparison set

1,454Raw benchmark valueCI 1,437 - 1,471

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 #11

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 96.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_business_and_management_and_financial_operations. Source rank: #14. Votes: 2736. Organization: meta. License: Proprietary.

96.9% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,449 - 1,473

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 #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,448
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_entertainment_and_sports_and_media. Source rank: #12. Votes: 2518. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,448Raw benchmark valueCI 1,436 - 1,460

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 #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_legal_and_government. Source rank: #6. Votes: 963. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,470 - 1,509

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 #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 96%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_life_and_physical_and_social_science. Source rank: #18. Votes: 2268. Organization: meta. License: Proprietary.

96% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,465 - 1,491

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #31

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 90.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_mathematical. Source rank: #38. Votes: 812. Organization: meta. License: Proprietary.

90.3% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,432 - 1,474

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_medicine_and_healthcare. Source rank: #10. Votes: 967. Organization: meta. License: Proprietary.

97.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,464 - 1,503

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 #17

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 95.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_software_and_it_services. Source rank: #20. Votes: 5323. Organization: meta. License: Proprietary.

95.1% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,475 - 1,492

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 #16

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,450
Percentile: 95.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: industry_writing_and_literature_and_language. Source rank: #20. Votes: 3138. Organization: meta. License: Proprietary.

95.4% percentile inside its fair comparison set

1,450Raw benchmark valueCI 1,439 - 1,461

Search / tool use1 benchmark88.3%

Tau2-Bench Telecom

AA · Search / tool use · Objective

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

Rank #37 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 91.5%
Percentile: 88.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `tau2`.

88.3% percentile inside its fair comparison set

91.5%Raw benchmark value

Long context2 benchmarks87.3%

Long Context Reasoning

AA · Long context · Objective

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

Rank #6 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 69.7%
Percentile: 98.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `lcr`.

98.4% percentile inside its fair comparison set

69.7%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 #22 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.1%
Percentile: 76.1%
Last updated: recent
Eligibility: benchmark_derived_model

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

76.1% percentile inside its fair comparison set

65.1%Raw benchmark valueCI 63.3% - 66.9%

Vision understanding16 benchmarks93.3%

MMMU-Pro

AA · Vision understanding · Objective

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

Rank #2 · Source label: Muse Spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 80.5%
Percentile: 99.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

99.3% percentile inside its fair comparison set

80.5%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,295
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 5613. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,295Raw benchmark valueCI 1,285 - 1,304

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,306
Percentile: 94.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing_vision. Source rank: #4. Votes: 338. Organization: meta. License: Proprietary.

94.5% percentile inside its fair comparison set

1,306Raw benchmark valueCI 1,273 - 1,340

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,312
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: diagram. Source rank: #10. Votes: 1526. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,312Raw benchmark valueCI 1,296 - 1,327

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,289
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 2336. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,289Raw benchmark valueCI 1,275 - 1,303

Vision Arena · Homework

AR · Vision understanding · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,297
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: homework. Source rank: #18. Votes: 940. Organization: meta. License: Proprietary.

80.9% percentile inside its fair comparison set

1,297Raw benchmark valueCI 1,278 - 1,317

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 #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,323
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: humor. Source rank: #1. Votes: 230. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,323Raw benchmark valueCI 1,283 - 1,364

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 #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 92.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: ocr. Source rank: #8. Votes: 4040. Organization: meta. License: Proprietary.

92.9% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,293 - 1,313

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,307
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #6. Votes: 5613. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,307Raw benchmark valueCI 1,298 - 1,317

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 94.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: creative_writing_vision. Source rank: #4. Votes: 338. Organization: meta. License: Proprietary.

94.5% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,296 - 1,363

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 #8

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,310
Percentile: 90%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: diagram. Source rank: #12. Votes: 1526. Organization: meta. License: Proprietary.

90% percentile inside its fair comparison set

1,310Raw benchmark valueCI 1,294 - 1,326

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 #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 97.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: english. Source rank: #6. Votes: 2336. Organization: meta. License: Proprietary.

97.2% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,289 - 1,317

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 #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,298
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: homework. Source rank: #18. Votes: 940. Organization: meta. License: Proprietary.

80.9% percentile inside its fair comparison set

1,298Raw benchmark valueCI 1,279 - 1,318

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 #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: humor. Source rank: #1. Votes: 230. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,302 - 1,383

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 #7

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,309
Percentile: 91.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: ocr. Source rank: #9. Votes: 4040. Organization: meta. License: Proprietary.

91.4% percentile inside its fair comparison set

1,309Raw benchmark valueCI 1,298 - 1,319

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 #8 · Source label: meta/muse_spark

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.4%
Percentile: 87.9%
Last updated: recent
Eligibility: benchmark_derived_model

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

87.9% percentile inside its fair comparison set

87.4%Raw benchmark valueCI 85.8% - 89%

Document understanding2 benchmarks60.4%

Document Arena

AR · Document understanding · Human

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

Rank #9

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,466
Percentile: 66.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #12. Votes: 1081. Organization: meta. License: Proprietary.

66.7% percentile inside its fair comparison set

1,466Raw benchmark valueCI 1,448 - 1,485

Document Arena · No Style Control

AR · Document understanding · Human

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

Rank #12

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 54.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: overall. Source rank: #15. Votes: 1081. Organization: meta. License: Proprietary.

54.2% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,424 - 1,460

Multilingual14 benchmarks97.3%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #10

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 96.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #14. Votes: 852. Organization: meta. License: Proprietary.

96.9% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,502 - 1,545

Text Arena · French

AR · Multilingual · Human

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

Rank #2

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,524
Percentile: 99.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: french. Source rank: #2. Votes: 468. Organization: meta. License: Proprietary.

99.5% percentile inside its fair comparison set

1,524Raw benchmark valueCI 1,495 - 1,554

Text Arena · German

AR · Multilingual · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: german. Source rank: #4. Votes: 234. Organization: meta. License: Proprietary.

98.7% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,466 - 1,546

Text Arena · Korean

AR · Multilingual · Human

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

Rank #1

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 100%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: korean. Source rank: #1. Votes: 254. Organization: meta. License: Proprietary.

100% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,440 - 1,518

Text Arena · Russian

AR · Multilingual · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 95.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: russian. Source rank: #19. Votes: 1482. Organization: meta. License: Proprietary.

95.5% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,464 - 1,496

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,482
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: spanish. Source rank: #6. Votes: 501. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,482Raw benchmark valueCI 1,455 - 1,510

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #14

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 95.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #19. Votes: 852. Organization: meta. License: Proprietary.

95.6% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,484 - 1,527

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: french. Source rank: #7. Votes: 468. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,471 - 1,529

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #6

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 97.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: german. Source rank: #6. Votes: 234. Organization: meta. License: Proprietary.

97.9% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,452 - 1,531

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #4

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,464
Percentile: 98.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: korean. Source rank: #4. Votes: 254. Organization: meta. License: Proprietary.

98.6% percentile inside its fair comparison set

1,464Raw benchmark valueCI 1,425 - 1,503

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #13

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 95.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: russian. Source rank: #17. Votes: 1482. Organization: meta. License: Proprietary.

95.8% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,449 - 1,481

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 98.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: spanish. Source rank: #6. Votes: 501. Organization: meta. License: Proprietary.

98.1% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,447 - 1,501

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,342
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #7. Votes: 447. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,342Raw benchmark valueCI 1,310 - 1,374

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #5

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 94.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `muse-spark`. Category: chinese. Source rank: #7. Votes: 447. Organization: meta. License: Proprietary.

94.8% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,323 - 1,386

Source links and registry checks

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Arena

Jun 20, 2026

source →

official

Artificial Analysis

Jun 20, 2026

source →

muse-spark

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

muse-spark

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks