Model comparison
Claude 3 Opus vs Claude Sonnet 4.5
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 29.3 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Claude Sonnet 4.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 24.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 77.8% for Claude Sonnet 4.5.
Side by side
| Claude 3 Opus | Claude Sonnet 4.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.3 | 44.0 |
| Released | 2024-02-29 | 2025-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 46 | 73 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude 3 Opus: 32.4 (#261), Claude Sonnet 4.5: 47.8 (#54)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| WeirdML | 19.2% | 47.7% |
| LMArena Coding | 1264 | 1489 |
| SWE-bench Verified | — | 71.3% |
| SWE-bench Verified (bash only) | — | 71.4% |
| LMArena WebDev | — | 1393 |
| SWE-bench Multilingual | — | 67% |
| SciCode | — | 44.7% |
| GSO | — | 14.7% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 796.15 |
| AlgoTune | — | 1.52 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude 3 Opus: 24.3 (#110), Claude Sonnet 4.5: 38.1 (#30)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| Cybench | 10% | 60% |
| METR Time Horizons | 29.5% | 67.4% |
| Terminal-Bench | — | 46.5% |
| Berkeley Function Calling Leaderboard | — | 73.2% |
| GDPval | — | 42.5% |
| Remote Labor Index | — | 2.1% |
| τ²-bench Airline | — | 72% |
| τ²-bench Banking | — | 25.3% |
| τ²-bench Retail | — | 72.4% |
| τ²-bench Telecom | — | 84.9% |
| DeepResearch Bench | — | 52.6% |
| OSWorld | — | 62.9% |
| LMArena Search | — | 1159 |
| Vending-Bench 2 | — | 3,839 |
Reasoning Claude Sonnet 4.5 leads
Claude 3 Opus: 14.2 (#318), Claude Sonnet 4.5: 26.9 (#113)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| SimpleBench | 23.5% | 54.3% |
| Chess Puzzles | 5% | 12% |
| EnigmaEval | 0.8% | 6% |
| LMArena Hard Prompts | 1246 | 1462 |
| DTBench | 61.6% | 83.2% |
| LMCA | 17% | 38.8% |
| Epoch Capabilities Index | 126.91 | 146.84 |
| ForecastBench | 58.4 | 61.9 |
| ARC-AGI-2 | — | 13.6% |
| Kagi LLM Benchmark | — | 57.9% |
| NYT Connections (extended) | — | 37.3% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 1.1% |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 17% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Sonnet 4.5 leads
Claude 3 Opus: 13.9 (#293), Claude Sonnet 4.5: 31.9 (#190)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 77.8% |
| LMArena Math | 1273 | 1448 |
| MATH Level 5 | 37.5% | 97.7% |
| FrontierMath (Tiers 1-3) | — | 23.9% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 19% |
| Omni-MATH | — | 55.3% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 15.2% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Sonnet 4.5 leads
Claude 3 Opus: 24.5 (#262), Claude Sonnet 4.5: 48.4 (#70)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| GPQA Diamond | 47.2% | 82.3% |
| SimpleQA Verified | 12.6% | 30.7% |
| LMArena Expert | 1223 | 1483 |
| Humanity's Last Exam | — | 13.7% |
| MMLU-Pro | — | 86.9% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 12% |
| GPQA (HELM) | — | 68.6% |
| MMLU | 84.6% | — |
Multimodal Claude Sonnet 4.5 leads
Claude 3 Opus: 26.6 (#112), Claude Sonnet 4.5: 34.1 (#84)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Vision | 1023 | — |
| VPCT | — | 39.8% |
| LMArena Document | — | 1450 |
Multilingual Claude Sonnet 4.5 leads
Claude 3 Opus: 41.6 (#202), Claude Sonnet 4.5: 53.6 (#65)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Non-English | 1258 | 1425 |
| LMArena Chinese | 1248 | 1459 |
| LMArena French | 1274 | 1459 |
| LMArena German | 1258 | 1427 |
| LMArena Japanese | 1204 | 1390 |
| LMArena Korean | 1187 | 1403 |
| LMArena Russian | 1280 | 1436 |
| LMArena Spanish | 1246 | 1457 |
Instruction Following Claude Sonnet 4.5 leads
Claude 3 Opus: 64.3 (#223), Claude Sonnet 4.5: 75.2 (#74)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1459 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 85% |
Long Context Claude Sonnet 4.5 leads
Claude 3 Opus: 38.2 (#197), Claude Sonnet 4.5: 45.2 (#45)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Longer Query | 1259 | 1476 |
Writing & Preference Claude Sonnet 4.5 leads
Claude 3 Opus: 47.4 (#208), Claude Sonnet 4.5: 66.7 (#33)
| Benchmark | Claude 3 Opus | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Text | 1262 | 1439 |
| LMArena Creative Writing | 1235 | 1442 |
| LMArena Multi-Turn | 1275 | 1465 |
| EQ-Bench Creative Writing | — | 1678 |
| WildBench | — | 85.4% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Sonnet 4.5?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 29.3 on the Noometry Index.
Is Claude 3 Opus or Claude Sonnet 4.5 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Sonnet 4.5 share?
31 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Sonnet 4.5 has 73.