Model comparison
Claude 3.7 Sonnet vs Llama 3-70B
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 28.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.7 Sonnet leads 35.7 to 12.0.
- The biggest single-benchmark swing is MATH Level 5: 91.2% for Claude 3.7 Sonnet and 22.6% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Llama 3-70B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.4 | 28.5 |
| Released | 2025-02-24 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 31 |
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 3-70B: 35.3 (#215)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1361 | 1206 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| BigCodeBench Instruct | — | 43.6% |
| LiveBench Coding | 74.5% | — |
| BigCodeBench Complete | — | 54.5% |
| CadEval | 54% | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.9 (#46), Llama 3-70B: 20.9 (#132)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| Cybench | 20% | 5% |
| TheAgentCompany | 30.9% | — |
| 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 3-70B: 17.4 (#284)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1195 |
| Epoch Capabilities Index | 141.16 | 122.91 |
| ForecastBench | 61.8 | 57.1 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 35.1% |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 54.2% |
| LiveBench Data Analysis | 74% | — |
| LiveBench | 76.1% | — |
| WinoGrande | — | 83.5% |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), Llama 3-70B: 12.0 (#299)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 4.3% |
| LMArena Math | 1336 | 1218 |
| MATH Level 5 | 91.2% | 22.6% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), Llama 3-70B: 20.8 (#272)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 79.7% | 40.6% |
| LMArena Expert | 1321 | 1149 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
| MMLU | — | 79.3% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), Llama 3-70B: —
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 44.3 (#174), Llama 3-70B: 33.8 (#246)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1296 | 1142 |
| LMArena Chinese | 1299 | 1114 |
| LMArena French | 1302 | 1231 |
| LMArena German | 1301 | 1169 |
| LMArena Japanese | 1268 | 1017 |
| LMArena Korean | 1249 | 1017 |
| LMArena Russian | 1311 | 1159 |
| LMArena Spanish | 1299 | 1241 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 73.1 (#120), Llama 3-70B: 62.8 (#233)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1352 | 1194 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Llama 3-70B: 35.6 (#235)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1373 | 1174 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.6 (#145), Llama 3-70B: 43.0 (#225)
| Benchmark | Claude 3.7 Sonnet | Llama 3-70B |
|---|---|---|
| LMArena Text | 1314 | 1221 |
| LMArena Creative Writing | 1332 | 1210 |
| LMArena Multi-Turn | 1339 | 1223 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Llama 3-70B?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 28.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Llama 3-70B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 35.3 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Llama 3-70B share?
23 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Llama 3-70B has 31.