Model comparison
Claude 3.5 Sonnet vs Claude Opus 4
Claude Opus 4 is the stronger model overall, scoring 42.9 to 34.4 on the Noometry Index.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and Claude Opus 4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4 leads 40.2 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 64.4% for Claude Opus 4.
Side by side
| Claude 3.5 Sonnet | Claude Opus 4 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 34.4 | 42.9 |
| Released | 2024-06-20 | 2025-05-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 32K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $75 |
| Results tracked | 60 | 56 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude 3.5 Sonnet: 39.5 (#145), Claude Opus 4: 47.8 (#55)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| Aider Polyglot | 51.6% | 72% |
| GSO | 4.6% | 6.9% |
| WeirdML | 40% | 43.7% |
| LMArena Coding | 1343 | 1442 |
| SWE-bench Verified | — | 70.7% |
| SWE-bench Verified (bash only) | — | 67.6% |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| AlgoTune | — | 1.33 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude Opus 4 leads
Claude 3.5 Sonnet: 32.1 (#61), Claude Opus 4: 34.5 (#39)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| Cybench | 17.5% | 38% |
| METR Time Horizons | 45.2% | 63.9% |
| TheAgentCompany | 24% | — |
| DeepResearch Bench | — | 46.8% |
| BALROG | 32.6% | — |
| LMArena Search | — | 1127 |
Reasoning Claude Opus 4 leads
Claude 3.5 Sonnet: 22.5 (#176), Claude Opus 4: 27.4 (#104)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| SimpleBench | 41.4% | 58.8% |
| EnigmaEval | 0.9% | 5.6% |
| LMArena Hard Prompts | 1305 | 1399 |
| DTBench | 67.8% | 81.6% |
| Epoch Capabilities Index | 133.55 | 142.67 |
| ForecastBench | 60.7 | 61.1 |
| ARC-AGI-2 | — | 8.6% |
| Kagi LLM Benchmark | — | 74.3% |
| ARC-AGI-1 | — | 35.7% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 37.4% |
| LiveBench | 59% | — |
Math Claude Opus 4 leads
Claude 3.5 Sonnet: 18.0 (#282), Claude Opus 4: 40.2 (#80)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 64.4% |
| Omni-MATH | 27.6% | 61.6% |
| LMArena Math | 1306 | 1391 |
| MATH Level 5 | 56.9% | 85% |
| FrontierMath (Feb 2025 set) | 2.1% | 4.5% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| LiveBench Math | 52.3% | — |
Knowledge Claude Opus 4 leads
Claude 3.5 Sonnet: 28.5 (#236), Claude Opus 4: 43.9 (#82)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| GPQA Diamond | 55.3% | 76.3% |
| Humanity's Last Exam | 4.1% | 10.7% |
| MMLU-Pro | 77.7% | 87.5% |
| Confabulations | 19.9% | 15.9% |
| GPQA (HELM) | 56.5% | 70.8% |
| LMArena Expert | 1264 | 1384 |
| Vectara Hallucination Rate | — | 12% |
| MMLU | 87.3% | — |
Multimodal Claude Opus 4 leads
Claude 3.5 Sonnet: 26.0 (#115), Claude Opus 4: 30.9 (#101)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Vision | 1125 | 1192 |
| GeoBench | 62% | 49% |
| VPCT | 33% | 38% |
| Video-MME | 60% | — |
Multilingual Claude Opus 4 leads
Claude 3.5 Sonnet: 43.4 (#180), Claude Opus 4: 49.0 (#133)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Non-English | 1283 | 1362 |
| LMArena Chinese | 1271 | 1386 |
| LMArena French | 1304 | 1370 |
| LMArena German | 1297 | 1391 |
| LMArena Japanese | 1234 | 1332 |
| LMArena Korean | 1200 | 1318 |
| LMArena Russian | 1305 | 1392 |
| LMArena Spanish | 1289 | 1388 |
Instruction Following Claude Opus 4 leads
Claude 3.5 Sonnet: 69.0 (#177), Claude Opus 4: 77.3 (#26)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| IFEval | 85.5% | 91.8% |
| LMArena Instruction Following | 1297 | 1406 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#162), Claude Opus 4: 39.5 (#167)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Longer Query | 1311 | 1422 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Claude Opus 4 leads
Claude 3.5 Sonnet: 53.0 (#159), Claude Opus 4: 61.4 (#85)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 4 |
|---|---|---|
| LMArena Text | 1298 | 1377 |
| LMArena Creative Writing | 1292 | 1386 |
| Short-Story Creative Writing | 80.3% | 83.6% |
| EQ-Bench Creative Writing | 1451 | 1580 |
| WildBench | 79.2% | 85.2% |
| LMArena Multi-Turn | 1326 | 1396 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Claude Opus 4?
Claude Opus 4 is the stronger model overall, scoring 42.9 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Claude Opus 4 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Claude Opus 4 share?
44 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude Opus 4 has 56.