Model comparison
Claude 3.7 Sonnet vs Claude Sonnet 5
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 39.5 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 Sonnet 5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 94.7% for Claude Sonnet 5.
Side by side
| Claude 3.7 Sonnet | Claude Sonnet 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.5 | 54.6 |
| Released | 2025-02-24 | 2026-06-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 58 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude 3.7 Sonnet: 40.6 (#136), Claude Sonnet 5: 55.5 (#26)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| GSO | 3.8% | 37.3% |
| LMArena Coding | 1361 | 1483 |
| SWE-bench Verified | 61% | — |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| CursorBench | — | 34.1% |
| LMArena WebDev | — | 1541 |
| SciCode | — | 54.3% |
| WeirdML | — | 68.8% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,463 |
Agentic & Tool Use Claude Sonnet 5 leads
Claude 3.7 Sonnet: 34.1 (#50), Claude Sonnet 5: 42.8 (#18)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| APEX-Agents | — | 54.5% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| GBAEval | — | 65.3% |
| LMArena Search | — | 1194 |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 6,378 |
Reasoning Claude Sonnet 5 leads
Claude 3.7 Sonnet: 18.6 (#277), Claude Sonnet 5: 49.1 (#39)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| SimpleBench | 46.4% | 60.6% |
| LMArena Hard Prompts | 1333 | 1461 |
| Epoch Capabilities Index | 141.16 | 156.21 |
| ForecastBench | 61.8 | 61.1 |
| ARC-AGI-2 | 0.9% | — |
| NYT Connections (extended) | — | 75.1% |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 16.9% |
| Chess Puzzles | — | 35% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 35% |
| DTBench | — | 92.5% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 50% |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |
| LiveBench | 76.1% | — |
Math Claude Sonnet 5 leads
Claude 3.7 Sonnet: 37.5 (#153), Claude Sonnet 5: 66.2 (#27)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 94.7% |
| LMArena Math | 1337 | 1467 |
| FrontierMath (Tiers 1-3) | — | 65.6% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 77% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude Sonnet 5 leads
Claude 3.7 Sonnet: 39.8 (#130), Claude Sonnet 5: 55.6 (#47)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 79.7% | 90.5% |
| LMArena Expert | 1321 | 1490 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 33.7% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Claude Sonnet 5 leads
Claude 3.7 Sonnet: 33.7 (#95), Claude Sonnet 5: 42.4 (#31)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | 1169 | 1274 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 24.9% |
| LMArena Document | — | 1466 |
| SpatialViz-Bench | 33.9% | — |
Multilingual Claude Sonnet 5 leads
Claude 3.7 Sonnet: 44.1 (#179), Claude Sonnet 5: 53.8 (#55)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1296 | 1431 |
| LMArena Chinese | 1299 | 1477 |
| LMArena French | 1303 | 1460 |
| LMArena German | 1301 | 1440 |
| LMArena Japanese | 1267 | 1422 |
| LMArena Korean | 1249 | 1411 |
| LMArena Russian | 1311 | 1451 |
| LMArena Spanish | 1298 | 1437 |
Instruction Following Claude Sonnet 5 leads
Claude 3.7 Sonnet: 72.9 (#125), Claude Sonnet 5: 76.3 (#41)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1452 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Claude Sonnet 5: 44.8 (#55)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1373 | 1463 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Claude Sonnet 5 leads
Claude 3.7 Sonnet: 54.4 (#150), Claude Sonnet 5: 69.2 (#25)
| Benchmark | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1314 | 1442 |
| LMArena Creative Writing | 1332 | 1416 |
| EQ-Bench Creative Writing | 1412 | 1794 |
| LMArena Multi-Turn | 1339 | 1454 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| EQ-Bench 4 | — | 1236 |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Claude Sonnet 5?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Claude Sonnet 5 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Claude Sonnet 5 share?
25 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Claude Sonnet 5 has 51.