- MMMU, 0-shot, accuracy 73.4
- MMMU Pro (avg of Standard and Vision) 59.6
- MathVista 73.7
- ChartQA, relaxed_accuracy 90
- DocVQA (test), anls 94.4
- LiveCodeBench (10/01/2024-02/01/2025), pass@1 43.4
- MMLU Pro, 0-shot, macro_avg/acc 80.5
- GPQA Diamond 69.8
- MGSM, average/em 92.3
- Best of MTOB (half book) eng->kgv/kgv->eng = 54.0/46.4 / MTOB (full book) eng->kgv/kgv->eng = 50.8/46.7 54
- MMLU (5-shot) [pretrained] 85.5
- MATH (4-shot, em_maj1@1) [pretrained] 61.2
- MBPP (3-shot, pass@1) [pretrained] 77.6
- TydiQA (1-shot, average/f1) [pretrained] 31.7
Llama 4 Maverick
Llama 4 Maverick places in the top three on BigCodeBench.
106
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Meta Apr 2025 Llama 4 Maverick
Open weights Open model
132.3
#155 of 271
Epoch Capabilities Index
- Humanity's Last Exam 5.68% #39 /47
- SWE-Bench Pro 5.24% #24 /24
- MMMU-Pro 59.6% #57 /72
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MGSM | 92.3% | #4 of 52 | Model card | |
| BullshitBench | 54.5% | #22 of 107 | Official leaderboard | |
| Phare | 70.8% | #16 of 62 | Official leaderboard | |
| MTOB | 54.0 | #1 of 3 | Model card | |
| Vectara Hallucination Leaderboard (2025 dataset) | 8.20% | #40 of 104 | Official leaderboard | |
| HELM Arabic | 79.1 | #11 of 28 | Official leaderboard | |
| MMLU | 85.5% | #51 of 127 | Model card | |
| Slop Score | 49.2 | #7 of 17 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 4.60% | #69 of 148 | Official leaderboard | |
| MMLU-Pro | 80.5% | #74 of 151 | Model card | |
| TydiQA | 31.7% | #1 of 2 | Model card | |
| HELM Arabic Enterprise | 64.8 | #13 of 23 | Official leaderboard | |
| BullshitBench V2 | 29% | #72 of 122 | Official leaderboard | |
| LMArena (Elo) | 1,327 | #198 of 333 | Official leaderboard | |
| FaithJudge | 20.6% | #22 of 37 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 1422.0 | #46 of 76 | Official leaderboard | |
| Arena-Hard v2.0 | 17.2% | #17 of 23 | Official leaderboard | |
| SEA-HELM | 61.3 | #47 of 62 | Official leaderboard | |
| LLM Confabulation Leaderboard | 22.6% | #44 of 58 | Official leaderboard | |
| Fiction.LiveBench | 46.2% | #46 of 57 | Epoch AI | |
| WritingBench | 52.5 | #37 of 45 | Official leaderboard | |
| Humanity's Last Exam | 5.68% | #39 of 47 | Official leaderboard | |
| Creative Writing v3 | 51.7 | #103 of 120 | Official leaderboard | |
| EQ-Bench 3 | 865 | #70 of 78 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 31.9 | #110 of 119 | Official leaderboard | |
| Lech Mazur Creative Writing | 6.20 | #42 of 44 | Epoch AI | |
| Extended NYT Connections | 8.00% | #94 of 97 | Official leaderboard | |
| MultiNRC | 8.44% | #38 of 38 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH Level 5 | 73% | #32 of 94 | Epoch AI | |
| ForecastBench | 61.8 | #34 of 86 | Official leaderboard | |
| GPQA Diamond | 67% | #113 of 219 | Epoch AI | |
| MATH | 61.2% | #51 of 93 | Model card | |
| PolyMath | 26.1% | #27 of 38 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 20.6% | #144 of 202 | Epoch AI | |
| DTBench | 36.5% | #133 of 178 | Official leaderboard | |
| SimpleBench | 27.7% | #79 of 100 | Official leaderboard | |
| Misguided Attention | 29.5% | #36 of 45 | Official leaderboard | |
| CritPt | 0% | #130 of 160 | Epoch AI | |
| FrontierMath | 0.69% | #63 of 70 | Epoch AI | |
| ARC-AGI-2 | 0% | #89 of 95 | Official leaderboard | |
| ARC-AGI | 4.38% | #89 of 92 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 55.5% | #3 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 28.4% | #28 of 96 | Official leaderboard | |
| MBPP | 77.6% | #25 of 66 | Model card | |
| Multi-SWE-bench | 6.13% | #5 of 11 | Official leaderboard | |
| LiveCodeBench | 43.4% | #47 of 73 | Model card | |
| BigO(Bench) | 32.8% | #14 of 18 | Official leaderboard | |
| LiveSQLBench | 13.2% | #31 of 36 | Official leaderboard | |
| Aider Polyglot | 15.6% | #47 of 54 | Epoch AI | |
| SWE-bench Verified | 21% | #54 of 60 | Official leaderboard | |
| WeirdML | 24.5% | #101 of 112 | Official leaderboard | |
| ALE-Bench | 173 | #120 of 121 | Epoch AI | |
| SWE-Bench Pro | 5.24% | #24 of 24 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 37.3% | #31 of 65 | Official leaderboard | |
| SnakeBench | 23 | #100 of 183 | Official leaderboard | |
| LLM Chess | -100 | #73 of 124 | Official leaderboard | |
| Elimination Game | 4 | #34 of 56 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 52.9% | #43 of 67 | Official leaderboard | |
| Step Race | 1 | #47 of 59 | Official leaderboard | |
| LisanBench | 131.0 | #107 of 133 | Official leaderboard | |
| Galileo Agent Leaderboard | 0.74 | #28 of 31 | Official leaderboard | |
| Meta Agents Research Environments (ARE) / Gaia2 | 7.40% | #12 of 13 | Official leaderboard | |
| PACT | 1,394 | #26 of 26 | Official leaderboard | |
| Agent Poker Bench | 891 | #17 of 17 | Official leaderboard | |
| VideoGameBench | 0% | #5 of 5 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LEXam | 47.3% | #15 of 31 | Official leaderboard | |
| LegalBench | 77.8% | #98 of 138 | Official leaderboard | |
| MedCode | 36.5% | #72 of 96 | Official leaderboard | |
| MortgageTax | 58.5% | #66 of 86 | Official leaderboard | |
| TaxEval v2 | 66.6% | #101 of 129 | Official leaderboard | |
| CorpFin v2 | 49.7% | #98 of 119 | Official leaderboard | |
| RadLE 2.0 | 263.0 | #10 of 12 | Official leaderboard | |
| Vals Finance Agent v1 | 3.63% | #44 of 47 | Official leaderboard | |
| ProfBench | 34.4% | #69 of 72 | Official leaderboard | |
| MedScribe | 54.2% | #96 of 98 | Official leaderboard | |
| PRBench | 24.8% | #44 of 44 | Official leaderboard | |
| Physical-Engineering's Last Exam | 0.01 | #18 of 18 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartQA | 90% | #6 of 37 | Model card | |
| MMMU | 73.4% | #26 of 136 | Official leaderboard | |
| DocVQA | 94.4% | #13 of 33 | Model card | |
| VHELM | 52.4 | #20 of 41 | Official leaderboard | |
| MathVista | 73.7% | #33 of 64 | Model card | |
| VISTA | 38.3% | #37 of 54 | Official leaderboard | |
| Vision Arena | 1,145 | #101 of 136 | Official leaderboard | |
| MMMU-Pro | 59.6% | #57 of 72 | Model card | |
| RoboRewardBench | 1.27 | #16 of 19 | Official leaderboard | |
| ZeroBench | 2.00% | #57 of 66 | Official leaderboard | |
| GeoBench | 52% | #42 of 48 | Official leaderboard | |
| EnigmaEval | 0.58% | #40 of 41 | Epoch AI | |
| SpatialViz-Bench | 31.8% | #8 of 8 | Epoch AI |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleSafetyTests | 99.3% | #29 of 75 | Official leaderboard | |
| AIR-Bench 2024 | 68.6% | #36 of 82 | Official leaderboard | |
| Spiral-Bench v1.2 | 38.2 | #11 of 21 | Official leaderboard | |
| HELM Safety | 90.6 | #43 of 75 | Official leaderboard | |
| BaxBench | 21.9% | #22 of 34 | Official leaderboard | |
| FORTRESS | 40.1% | #44 of 66 | Official leaderboard | |
| Spiral-Bench v1.0 | 48.1 | #9 of 13 | Official leaderboard | |
| Anthropic Red Team | 98.2% | #55 of 75 | Official leaderboard | |
| KORA | 22.9% | #34 of 42 | Official leaderboard | |
| DistressBench | 41.3% | #42 of 42 | Official leaderboard | |
| Dictatorship Eval | 0% | #20 of 20 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Capabilities | 71.8 | #19 of 60 | Official leaderboard | |
| ACCoRD | 50.2 | #111 of 150 | Official leaderboard | |
| SAGE (Vals) | 35.7% | #65 of 81 | Official leaderboard | |
| Conceptual Reasoning Index | 26.8 | #120 of 149 | Official leaderboard | |
| LMCA | 15.9% | #116 of 139 | Epoch AI |
Meta's models over time
Meta's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.