Model comparison
Claude 3.7 Sonnet vs Claude Opus 4
Claude Opus 4 is the stronger model overall, scoring 42.9 to 39.4 on the Noometry Index.
Last verified . 47 shared benchmarks.
Summary
- They share 47 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 2 categories and Claude Opus 4 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.2 to 39.5.
- The biggest single-benchmark swing is Omni-MATH: 33% for Claude 3.7 Sonnet and 61.6% for Claude Opus 4.
Side by side
| Claude 3.7 Sonnet | Claude Opus 4 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.4 | 42.9 |
| Released | 2025-02-24 | 2025-05-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 32K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $75 |
| Results tracked | 58 | 56 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude 3.7 Sonnet: 41.1 (#120), Claude Opus 4: 47.8 (#55)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| SWE-bench Verified | 61% | 70.7% |
| SWE-bench Verified (bash only) | 52.8% | 67.6% |
| Aider Polyglot | 64.9% | 72% |
| GSO | 3.8% | 6.9% |
| LMArena Coding | 1361 | 1442 |
| WeirdML | — | 43.7% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| AlgoTune | — | 1.33 |
Agentic & Tool Use Too close to call
Claude 3.7 Sonnet: 33.9 (#46), Claude Opus 4: 34.5 (#39)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| Cybench | 20% | 38% |
| DeepResearch Bench | 43.6% | 46.8% |
| METR Time Horizons | 60% | 63.9% |
| TheAgentCompany | 30.9% | — |
| OSWorld | 35.8% | — |
| LMArena Search | — | 1127 |
Reasoning Claude Opus 4 leads
Claude 3.7 Sonnet: 18.7 (#252), Claude Opus 4: 27.4 (#104)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 8.6% |
| SimpleBench | 46.4% | 58.8% |
| ARC-AGI-1 | 28.6% | 35.7% |
| EnigmaEval | 4.2% | 5.6% |
| LMArena Hard Prompts | 1333 | 1399 |
| Epoch Capabilities Index | 141.16 | 142.67 |
| ForecastBench | 61.8 | 61.1 |
| Kagi LLM Benchmark | — | 74.3% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | 87.8% | — |
| DTBench | — | 81.6% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 37.4% |
| LiveBench | 76.1% | — |
Math Claude Opus 4 leads
Claude 3.7 Sonnet: 35.7 (#137), Claude Opus 4: 40.2 (#80)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 64.4% |
| Omni-MATH | 33% | 61.6% |
| LMArena Math | 1336 | 1391 |
| MATH Level 5 | 91.2% | 85% |
| FrontierMath (Feb 2025 set) | 4.1% | 4.5% |
| LiveBench Math | 79% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 4 leads
Claude 3.7 Sonnet: 39.7 (#117), Claude Opus 4: 43.9 (#82)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| GPQA Diamond | 79.7% | 76.3% |
| Humanity's Last Exam | 8% | 10.7% |
| MMLU-Pro | 78.4% | 87.5% |
| Confabulations | 14.7% | 15.9% |
| GPQA (HELM) | 60.8% | 70.8% |
| LMArena Expert | 1321 | 1384 |
| Vectara Hallucination Rate | — | 12% |
Multimodal Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 33.1 (#90), Claude Opus 4: 30.9 (#101)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Vision | 1169 | 1192 |
| GeoBench | 68% | 49% |
| VPCT | 39% | 38% |
| SpatialViz-Bench | 33.9% | — |
Multilingual Claude Opus 4 leads
Claude 3.7 Sonnet: 44.3 (#174), Claude Opus 4: 49.0 (#133)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Non-English | 1296 | 1362 |
| LMArena Chinese | 1299 | 1386 |
| LMArena French | 1302 | 1370 |
| LMArena German | 1301 | 1391 |
| LMArena Japanese | 1268 | 1332 |
| LMArena Korean | 1249 | 1318 |
| LMArena Russian | 1311 | 1392 |
| LMArena Spanish | 1299 | 1388 |
Instruction Following Claude Opus 4 leads
Claude 3.7 Sonnet: 73.1 (#120), Claude Opus 4: 77.3 (#26)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| IFEval | 83.4% | 91.8% |
| LMArena Instruction Following | 1352 | 1406 |
| LiveBench Instruction Following | 81.3% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Claude Opus 4: 39.5 (#167)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| Fiction.LiveBench | 83.3% | 61.1% |
| LMArena Longer Query | 1373 | 1422 |
Writing & Preference Claude Opus 4 leads
Claude 3.7 Sonnet: 54.6 (#145), Claude Opus 4: 61.4 (#85)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Text | 1314 | 1377 |
| LMArena Creative Writing | 1332 | 1386 |
| Short-Story Creative Writing | 81.1% | 83.6% |
| EQ-Bench Creative Writing | 1412 | 1580 |
| WildBench | 81.4% | 85.2% |
| LMArena Multi-Turn | 1339 | 1396 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Claude Opus 4?
Claude Opus 4 is the stronger model overall, scoring 42.9 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Claude Opus 4 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 41.1 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Claude Opus 4 share?
47 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Claude Opus 4 has 56.