Llama 4 Maverick: benchmark scores, price and ranking
Llama 4 Maverick from Meta AI ranks #717 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.0), based on 11 benchmark results captured up to 2026-10-13.
- Organisation
- Meta AI
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-04-05 (source: curated)
- Cheapest API price
- $0.188 in / $0.652 out per million tokens (via openrouter, observed 2026-10-13T19:47Z)
- Aggregate rank
- #717 of 743 (score 42.0)
Relative to other models, Llama 4 Maverick is strongest on Epoch ECI (#82 of 204) and weakest on ARC-AGI-2 (#84 of 87).
Across the 11 benchmarks where at least ten models are scored, Llama 4 Maverick is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $0.188 per million tokens, is lower than that of 70% of the 427 models with a listed price.
Llama 4 Maverick benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 132 | #82 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 61.9% | #94 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Humanity's Last Exam | 5.7% | #19 of 27 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 27.7% | #44 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 15.9% | #84 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 33.1% | #88 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 24.5% | #91 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Aider Polyglot | 15.6% | #42 of 49 | Aider polyglot leaderboard | 2026-10-13 |
| CritPt | 0.0% | #99 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| EnigmaEval | 0.6% | #23 of 24 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ARC-AGI-2 | 0.0% | #84 of 87 | ARC Prize official leaderboard | 2026-10-13 |
About Llama 4 Maverick
Llama 4 Maverick is an open-weight model that can run on your own hardware from Meta AI. It was released on 2025-04-05, according to the developer's announcement. The cheapest API listing we track charges $0.188 per million input tokens and $0.652 per million output tokens, through openrouter. We hold 11 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where Llama 4 Maverick stands
On our aggregate score, Llama 4 Maverick is #717 of 743 ranked models, in the lower half. Its score is 42.0; the scale is centred on 50, so it sits 8.0 points below the typical model. That beats 3% of the ranked field. Among the 28 ranked Meta AI models it is #23. The next one up is Llama 3.2 1B at 42.0. The next one down is Llama-3.2-1B-Instruct at 41.1.
Llama 4 Maverick, benchmark by benchmark
Epoch ECI puts Llama 4 Maverick at 132, #82 of 204. That beats 60% of the models tested, but 24 points short of Qwen 3.8 Max (156). The results either side are DeepSeek-V3 (132) and Mistral Small 3.2 (132). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Llama 4 Maverick is 5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama 4 Maverick lands below the middle on DTBench: 61.9%, #94 of 146, with 64% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is mistral-medium-2505 at 62.3%. It covers dynamic tool-use benchmark. The board median is 68.8%, so Llama 4 Maverick is 6.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama 4 Maverick lands below the middle on Humanity's Last Exam: 5.7%, #19 of 27, with 67% of the field scoring higher. Muse Spark leads at 40.6%; the closest result above is Gemini 2.0 Flash Thinking Exp at 6.6%. It covers expert-level questions across domains. The board median is 10.7%, so Llama 4 Maverick is 5.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama 4 Maverick lands below the middle on SimpleBench: 27.7%, #44 of 61, with 70% of the field scoring higher. Claude Fable 5 (max) leads at 81.9%; the closest result above is Gemini 2.0 Flash Thinking Exp at 30.7%. It covers trick questions that test common sense. The board median is 41.4%, so Llama 4 Maverick is 13.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Llama 4 Maverick lands below the middle on LMCA: 15.9%, #84 of 108, with 77% of the field scoring higher. Claude Opus 5.5 (max) leads at 68.2%; the closest result above is GPT-4o (May 2024) at 16.6%. It covers language-model capability assessment. The board median is 29.2%, so Llama 4 Maverick is 13.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SciCode is a weak spot. Llama 4 Maverick scores 33.1%, #88 of 106, behind 82% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so Llama 4 Maverick is 11.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Aider Polyglot is a weak spot. Llama 4 Maverick scores 15.6%, #42 of 49, behind 84% of the models measured. The leader, gemini-2.5-pro-preview-06-05, reaches 83.1%. It covers edits across 6 languages (225 exercises). The board median is 44.9%, so Llama 4 Maverick is 29.3 points below it. Source: Aider polyglot leaderboard, captured 2026-10-13.
CritPt is a weak spot. Llama 4 Maverick scores 0.0%, #99 of 115, behind 85% of the models measured. The leader, GPT-5.6 Sol (max), reaches 32.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so Llama 4 Maverick is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
EnigmaEval is a weak spot. Llama 4 Maverick scores 0.6%, #23 of 24, behind 92% of the models measured. The leader, Gemini 3 Pro Preview, reaches 18.2%. It covers multi-step puzzle hunts. The board median is 2.9%, so Llama 4 Maverick is 2.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
ARC-AGI-2 is a weak spot. Llama 4 Maverick scores 0.0%, #84 of 87, behind 95% of the models measured. The leader, GPT-6 Astra (max), reaches 95.0%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Llama 4 Maverick is 22.8 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.
The full table above also lists the other 1 result, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Software engineering: weak, ahead of 16% of the field on average across 2 benchmarks. Its best board here is SciCode (#88 of 106) and its weakest is Aider Polyglot (#42 of 49). Reasoning, maths and science: weak, ahead of 16% of the field on average across 5 benchmarks. Its best board here is Humanity's Last Exam (#19 of 27) and its weakest is ARC-AGI-2 (#84 of 87). General knowledge and chat: uneven, ahead of 33% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#82 of 204) and its weakest is WeirdML (#91 of 109).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Llama 4 Maverick costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Trinity Large Thinking ($0.250) and GPT-4.1 mini ($0.400).
Release history
The Meta AI model released before it was Llama-3.3-70B-Instruct on 2024-12-06, which scores 40.7. The next one was Llama 4 Maverick (FP8) on 2025-04-05, at 45.6.
Reading these numbers
The 11 scores on this page come from 3 sources: Epoch AI Benchmarking Hub (9), ARC Prize official leaderboard (1), Aider polyglot leaderboard (1). 2 of them come from an official leaderboard and 9 from datasets or third-party runs.
Models ranked nearby
- #714 SmolLM2-135M (42.0)
- #715 SmolLM2-360M (42.0)
- #716 gemini-1.5-flash-8b-001 (42.0)
- #718 Mistral-7B-Instruct-v0.3 (41.9)
- #719 mistral-small-2503 (41.9)
- #720 claude-3-sonnet-20240229 (41.9)
More from Meta AI
- Muse Spark 1.3 (max) (#18, 55.1)
- Muse Spark (#29, 53.7)
- Muse Spark 1.1 (xhigh) (#66, 52.4)
- Muse Spark 1.2 (xhigh) (#113, 51.5)
- Llama 3.1-405B (#142, 51.2)
- Muse Wonder (max) (#209, 50.1)
Compare it on the live leaderboard → · How the aggregate score works