Model comparison
Claude 3.7 Sonnet vs Llama 4 Maverick
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 30.6 on the Noometry Index.
Last verified . 42 shared benchmarks.
MetaSummary
- They share 42 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.2 to 31.4.
- The biggest single-benchmark swing is Aider Polyglot: 64.9% for Claude 3.7 Sonnet and 15.6% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Llama 4 Maverick | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.4 | 30.6 |
| Released | 2025-02-24 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 58 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | 52.8% | 21% |
| Aider Polyglot | 64.9% | 15.6% |
| LMArena Coding | 1361 | 1302 |
| SWE-bench Verified | 61% | — |
| SciCode | — | 33.1% |
| GSO | 3.8% | — |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| LiveBench Coding | 74.5% | — |
| BigCodeBench Complete | — | 61.4% |
| CadEval | 54% | — |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), Llama 4 Maverick: 27.9 (#86)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.7 (#252), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 0.9% | 0% |
| SimpleBench | 46.4% | 27.7% |
| ARC-AGI-1 | 28.6% | 4.4% |
| EnigmaEval | 4.2% | 0.6% |
| LMArena Hard Prompts | 1333 | 1281 |
| Epoch Capabilities Index | 141.16 | 132.2 |
| ForecastBench | 61.8 | 57.5 |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| CritPt | — | 0% |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 61.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 15.9% |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 20.6% |
| Omni-MATH | 33% | 42.2% |
| LMArena Math | 1336 | 1299 |
| MATH Level 5 | 91.2% | 73% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.7% |
| LiveBench Math | 79% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 79.7% | 67% |
| Humanity's Last Exam | 8% | 5.7% |
| MMLU-Pro | 78.4% | 81% |
| Confabulations | 14.7% | 22.6% |
| GPQA (HELM) | 60.8% | 65% |
| LMArena Expert | 1321 | 1259 |
| Vectara Hallucination Rate | — | 8.2% |
Multimodal Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.1 (#90), Llama 4 Maverick: 30.9 (#100)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1169 | 1141 |
| GeoBench | 68% | 52% |
| SpatialViz-Bench | 33.9% | 31.8% |
| VPCT | 39% | — |
Multilingual Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 44.3 (#174), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1296 | 1269 |
| LMArena Chinese | 1299 | 1277 |
| LMArena French | 1302 | 1258 |
| LMArena German | 1301 | 1291 |
| LMArena Japanese | 1268 | 1207 |
| LMArena Korean | 1249 | 1203 |
| LMArena Russian | 1311 | 1286 |
| LMArena Spanish | 1299 | 1293 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 73.1 (#120), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| IFEval | 83.4% | 90.8% |
| LMArena Instruction Following | 1352 | 1267 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | 83.3% | 46.2% |
| LMArena Longer Query | 1373 | 1280 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Claude 3.7 Sonnet | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1314 | 1287 |
| LMArena Creative Writing | 1332 | 1266 |
| Short-Story Creative Writing | 81.1% | 62% |
| EQ-Bench Creative Writing | 1412 | 860 |
| WildBench | 81.4% | 80% |
| LMArena Multi-Turn | 1339 | 1289 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Llama 4 Maverick?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 30.6 on the Noometry Index.
Is Claude 3.7 Sonnet or Llama 4 Maverick better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 26.3 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Llama 4 Maverick share?
42 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Llama 4 Maverick has 54.