Model comparison
Claude 3 Opus vs Claude Sonnet 4.6
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 29.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Claude Sonnet 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 85.8% for Claude Sonnet 4.6.
Side by side
| Claude 3 Opus | Claude Sonnet 4.6 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.5 | 50.3 |
| Released | 2024-02-29 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 46 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude 3 Opus: 32.9 (#267), Claude Sonnet 4.6: 46.3 (#67)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| WeirdML | 19.2% | 66.1% |
| LMArena Coding | 1264 | 1504 |
| SWE-bench Verified | — | 75.2% |
| DeepSWE | — | 29.9% |
| FrontierCode | — | 24.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 46.8% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,327 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude 3 Opus: 24.6 (#116), Claude Sonnet 4.6: 39.1 (#28)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| Terminal-Bench | — | 53.4% |
| APEX-Agents | — | 43% |
| OSWorld 2.0 | — | 9.3% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 54.9% |
| OSWorld | — | 72.1% |
| ExploitBench | — | 23.6% |
| GBAEval | — | 48.8% |
| GDP.pdf | — | 18% |
| LMArena Search | — | 1221 |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 7,204 |
Reasoning Claude Sonnet 4.6 leads
Claude 3 Opus: 14.6 (#324), Claude Sonnet 4.6: 46.1 (#45)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| Chess Puzzles | 5% | 13% |
| LMArena Hard Prompts | 1245 | 1484 |
| DTBench | 61.6% | 89.9% |
| LMCA | 17% | 46.5% |
| Epoch Capabilities Index | 126.91 | 152.24 |
| ForecastBench | 58.4 | 62 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 80.9% |
| ARC-AGI-1 | — | 86.5% |
| CritPt | — | 3.1% |
| EnigmaEval | 0.8% | — |
| Thematic Generalization | — | 76.3% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 16% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Sonnet 4.6 leads
Claude 3 Opus: 14.8 (#299), Claude Sonnet 4.6: 52.9 (#49)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 85.8% |
| LMArena Math | 1273 | 1462 |
| ProofBench | — | 45% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Claude Sonnet 4.6 leads
Claude 3 Opus: 24.5 (#267), Claude Sonnet 4.6: 51.7 (#65)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| GPQA Diamond | 47.2% | 87.4% |
| SimpleQA Verified | 12.6% | 35.5% |
| LMArena Expert | 1223 | 1500 |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 10.6% |
| MMLU | 84.6% | — |
Multimodal Claude Sonnet 4.6 leads
Claude 3 Opus: 27.1 (#116), Claude Sonnet 4.6: 38.0 (#68)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Vision | 1023 | 1283 |
| Blueprint-Bench 2 | — | 6.7% |
| LMArena Document | — | 1482 |
Multilingual Claude Sonnet 4.6 leads
Claude 3 Opus: 41.4 (#207), Claude Sonnet 4.6: 54.4 (#41)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Non-English | 1258 | 1440 |
| LMArena Chinese | 1248 | 1491 |
| LMArena French | 1275 | 1465 |
| LMArena German | 1258 | 1428 |
| LMArena Japanese | 1204 | 1420 |
| LMArena Korean | 1187 | 1411 |
| LMArena Russian | 1280 | 1440 |
| LMArena Spanish | 1246 | 1464 |
Instruction Following Claude Sonnet 4.6 leads
Claude 3 Opus: 64.1 (#228), Claude Sonnet 4.6: 77.4 (#25)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1475 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Claude Sonnet 4.6 leads
Claude 3 Opus: 38.2 (#202), Claude Sonnet 4.6: 45.3 (#44)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Longer Query | 1259 | 1479 |
Writing & Preference Claude Sonnet 4.6 leads
Claude 3 Opus: 47.2 (#213), Claude Sonnet 4.6: 70.2 (#22)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Text | 1262 | 1458 |
| LMArena Creative Writing | 1235 | 1435 |
| LMArena Multi-Turn | 1275 | 1464 |
| EQ-Bench Creative Writing | — | 1810 |
| EQ-Bench 4 | — | 1207 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Sonnet 4.6?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Claude Sonnet 4.6 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Sonnet 4.6 share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Sonnet 4.6 has 57.