Model comparison
Claude 3.7 Sonnet vs Claude Opus 5
Claude Opus 5 is the stronger model overall, scoring 67.7 to 39.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Claude Opus 5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.1 to 18.7.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 90.4% for Claude Opus 5.
Side by side
| Claude 3.7 Sonnet | Claude Opus 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.4 | 67.7 |
| Released | 2025-02-24 | 2026-07-24 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 58 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude 3.7 Sonnet: 41.1 (#120), Claude Opus 5: 67.0 (#5)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Coding | 1361 | 1533 |
| SWE-bench Verified | 61% | — |
| DeepSWE | — | 73.6% |
| FrontierCode | — | 53.4% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| CursorBench | — | 46.6% |
| LMArena WebDev | — | 1694 |
| FrontierSWE | — | 52% |
| SciCode | — | 56.4% |
| GSO | 3.8% | — |
| WeirdML | — | 91.8% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 2,165 |
Agentic & Tool Use Claude Opus 5 leads
Claude 3.7 Sonnet: 33.9 (#46), Claude Opus 5: 55.5 (#1)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| APEX-Agents | — | 65.8% |
| OSWorld 2.0 | — | 31.4% |
| TheAgentCompany | 30.9% | — |
| τ²-bench Banking | — | 48.7% |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| PostTrainBench | — | 35% |
| BALROG | — | 63.4% |
| GBAEval | — | 79.6% |
| GDP.pdf | — | 24% |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 11,182 |
Reasoning Claude Opus 5 leads
Claude 3.7 Sonnet: 18.7 (#252), Claude Opus 5: 77.1 (#3)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| ARC-AGI-2 | 0.9% | 90.4% |
| SimpleBench | 46.4% | 80.6% |
| ARC-AGI-1 | 28.6% | 97.5% |
| LMArena Hard Prompts | 1333 | 1525 |
| Epoch Capabilities Index | 141.16 | 162.67 |
| NYT Connections (extended) | — | 94.3% |
| CritPt | — | 29.1% |
| Chess Puzzles | — | 42% |
| EnigmaEval | 4.2% | — |
| EBR-Bench | — | 45.7% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 59% |
| DTBench | — | 97.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 64.5% |
| Bench to the Future 3 | — | 0.12 |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Claude Opus 5 leads
Claude 3.7 Sonnet: 35.7 (#137), Claude Opus 5: 86.1 (#6)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 98.9% |
| LMArena Math | 1336 | 1533 |
| FrontierMath (Tiers 1-3) | — | 85.6% |
| FrontierMath Tier 4 | — | 73.2% |
| ProofBench | — | 99% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude Opus 5 leads
Claude 3.7 Sonnet: 39.7 (#117), Claude Opus 5: 66.8 (#8)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| GPQA Diamond | 79.7% | 93.9% |
| LMArena Expert | 1321 | 1558 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 59.9% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Claude Opus 5 leads
Claude 3.7 Sonnet: 33.1 (#90), Claude Opus 5: 51.1 (#6)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Vision | 1169 | 1321 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 30.4% |
| Furniture Assembly | — | 60.8% |
| LMArena Document | — | 1516 |
| SpatialViz-Bench | 33.9% | — |
Multilingual Claude Opus 5 leads
Claude 3.7 Sonnet: 44.3 (#174), Claude Opus 5: 58.8 (#3)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Non-English | 1296 | 1500 |
| LMArena Chinese | 1299 | 1575 |
| LMArena French | 1302 | 1522 |
| LMArena German | 1301 | 1522 |
| LMArena Japanese | 1268 | 1510 |
| LMArena Korean | 1249 | 1526 |
| LMArena Russian | 1311 | 1507 |
| LMArena Spanish | 1299 | 1519 |
Instruction Following Claude Opus 5 leads
Claude 3.7 Sonnet: 73.1 (#120), Claude Opus 5: 79.3 (#5)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1516 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.2 (#10), Claude Opus 5: 46.5 (#20)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Longer Query | 1373 | 1516 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Claude Opus 5 leads
Claude 3.7 Sonnet: 54.6 (#145), Claude Opus 5: 79.3 (#2)
| Benchmark | Claude 3.7 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Text | 1314 | 1506 |
| LMArena Creative Writing | 1332 | 1491 |
| EQ-Bench Creative Writing | 1412 | 2133 |
| LMArena Multi-Turn | 1339 | 1496 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1385 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Claude Opus 5?
Claude Opus 5 is the stronger model overall, scoring 67.7 to 39.4 on the Noometry Index.
Is Claude 3.7 Sonnet or Claude Opus 5 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 41.1 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Claude Opus 5 share?
25 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Claude Opus 5 has 57.