Model comparison
Claude 3 Opus vs Claude Sonnet 5
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Claude Sonnet 5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 94.7% for Claude Sonnet 5.
Side by side
| Claude 3 Opus | Claude Sonnet 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.5 | 54.6 |
| Released | 2024-02-29 | 2026-06-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 46 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude 3 Opus: 32.9 (#267), Claude Sonnet 5: 55.5 (#26)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| WeirdML | 19.2% | 68.8% |
| LMArena Coding | 1264 | 1483 |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| CursorBench | — | 34.1% |
| LMArena WebDev | — | 1541 |
| SciCode | — | 54.3% |
| GSO | — | 37.3% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,463 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude 3 Opus: 24.6 (#116), Claude Sonnet 5: 42.8 (#18)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| APEX-Agents | — | 54.5% |
| Cybench | 10% | — |
| GBAEval | — | 65.3% |
| LMArena Search | — | 1194 |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 6,378 |
Reasoning Claude Sonnet 5 leads
Claude 3 Opus: 14.6 (#324), Claude Sonnet 5: 49.1 (#39)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| SimpleBench | 23.5% | 60.6% |
| Chess Puzzles | 5% | 35% |
| LMArena Hard Prompts | 1245 | 1461 |
| DTBench | 61.6% | 92.5% |
| LMCA | 17% | 50% |
| Epoch Capabilities Index | 126.91 | 156.21 |
| ForecastBench | 58.4 | 61.1 |
| NYT Connections (extended) | — | 75.1% |
| CritPt | — | 16.9% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 35% |
| LiveBench Data Analysis | 57.9% | — |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Sonnet 5 leads
Claude 3 Opus: 14.8 (#299), Claude Sonnet 5: 66.2 (#27)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 94.7% |
| LMArena Math | 1273 | 1467 |
| FrontierMath (Tiers 1-3) | — | 65.6% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 77% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Claude Sonnet 5 leads
Claude 3 Opus: 24.5 (#267), Claude Sonnet 5: 55.6 (#47)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 47.2% | 90.5% |
| SimpleQA Verified | 12.6% | 33.7% |
| LMArena Expert | 1223 | 1490 |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Claude Sonnet 5 leads
Claude 3 Opus: 27.1 (#116), Claude Sonnet 5: 42.4 (#31)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | 1023 | 1274 |
| Blueprint-Bench 2 | — | 24.9% |
| LMArena Document | — | 1466 |
Multilingual Claude Sonnet 5 leads
Claude 3 Opus: 41.4 (#207), Claude Sonnet 5: 53.8 (#55)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1258 | 1431 |
| LMArena Chinese | 1248 | 1477 |
| LMArena French | 1275 | 1460 |
| LMArena German | 1258 | 1440 |
| LMArena Japanese | 1204 | 1422 |
| LMArena Korean | 1187 | 1411 |
| LMArena Russian | 1280 | 1451 |
| LMArena Spanish | 1246 | 1437 |
Instruction Following Claude Sonnet 5 leads
Claude 3 Opus: 64.1 (#228), Claude Sonnet 5: 76.3 (#41)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1452 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Claude Sonnet 5 leads
Claude 3 Opus: 38.2 (#202), Claude Sonnet 5: 44.8 (#55)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1259 | 1463 |
Writing & Preference Claude Sonnet 5 leads
Claude 3 Opus: 47.2 (#213), Claude Sonnet 5: 69.2 (#25)
| Benchmark | Claude 3 Opus | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1262 | 1442 |
| LMArena Creative Writing | 1235 | 1416 |
| LMArena Multi-Turn | 1275 | 1454 |
| EQ-Bench Creative Writing | — | 1794 |
| EQ-Bench 4 | — | 1236 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Sonnet 5?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Claude Sonnet 5 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Sonnet 5 share?
28 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Sonnet 5 has 51.