Model comparison
Claude 3.5 Sonnet vs Claude Opus 5
Claude Opus 5 is the stronger model overall, scoring 67.8 to 34.6 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Claude Opus 5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 98.9% for Claude Opus 5.
Side by side
| Claude 3.5 Sonnet | Claude Opus 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 34.6 | 67.8 |
| Released | 2024-06-20 | 2026-07-24 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 60 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude 3.5 Sonnet: 39.0 (#165), Claude Opus 5: 67.5 (#5)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| WeirdML | 40% | 91.8% |
| LMArena Coding | 1342 | 1534 |
| DeepSWE | — | 73.6% |
| FrontierCode | — | 53.4% |
| Aider Polyglot | 51.6% | — |
| CursorBench | — | 46.6% |
| LMArena WebDev | — | 1691 |
| FrontierSWE | — | 52% |
| SciCode | — | 56.4% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 2,165 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude Opus 5 leads
Claude 3.5 Sonnet: 32.3 (#67), Claude Opus 5: 55.6 (#1)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| BALROG | 32.6% | 63.4% |
| APEX-Agents | — | 65.8% |
| OSWorld 2.0 | — | 31.4% |
| TheAgentCompany | 24% | — |
| τ²-bench Banking | — | 48.7% |
| Cybench | 17.5% | — |
| PostTrainBench | — | 35% |
| GBAEval | — | 79.6% |
| GDP.pdf | — | 24% |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 11,182 |
Reasoning Claude Opus 5 leads
Claude 3.5 Sonnet: 23.1 (#183), Claude Opus 5: 77.2 (#4)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| SimpleBench | 41.4% | 80.6% |
| LMArena Hard Prompts | 1305 | 1526 |
| DTBench | 67.8% | 97.9% |
| Epoch Capabilities Index | 133.55 | 162.78 |
| ARC-AGI-2 | — | 90.4% |
| NYT Connections (extended) | — | 94.3% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 29.1% |
| Chess Puzzles | — | 42% |
| EnigmaEval | 0.9% | — |
| EBR-Bench | — | 45.7% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 59% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 64.5% |
| Bench to the Future 3 | — | 0.12 |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Claude Opus 5 leads
Claude 3.5 Sonnet: 19.2 (#288), Claude Opus 5: 86.2 (#8)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 98.9% |
| LMArena Math | 1307 | 1531 |
| FrontierMath (Tiers 1-3) | — | 85.6% |
| FrontierMath Tier 4 | — | 73.2% |
| ProofBench | — | 99% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Opus 5 leads
Claude 3.5 Sonnet: 28.6 (#245), Claude Opus 5: 66.8 (#9)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| GPQA Diamond | 55.3% | 93.9% |
| LMArena Expert | 1265 | 1557 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 59.9% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Claude Opus 5 leads
Claude 3.5 Sonnet: 26.5 (#120), Claude Opus 5: 50.8 (#8)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Vision | 1125 | 1319 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 30.4% |
| Furniture Assembly | — | 60.8% |
| LMArena Document | — | 1516 |
Multilingual Claude Opus 5 leads
Claude 3.5 Sonnet: 43.2 (#185), Claude Opus 5: 58.8 (#4)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Non-English | 1283 | 1501 |
| LMArena Chinese | 1272 | 1574 |
| LMArena French | 1305 | 1519 |
| LMArena German | 1297 | 1524 |
| LMArena Japanese | 1234 | 1516 |
| LMArena Korean | 1200 | 1521 |
| LMArena Russian | 1306 | 1507 |
| LMArena Spanish | 1290 | 1519 |
Instruction Following Claude Opus 5 leads
Claude 3.5 Sonnet: 68.8 (#182), Claude Opus 5: 79.2 (#7)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1517 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Claude Opus 5 leads
Claude 3.5 Sonnet: 39.9 (#167), Claude Opus 5: 46.5 (#21)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Longer Query | 1311 | 1515 |
Writing & Preference Claude Opus 5 leads
Claude 3.5 Sonnet: 52.9 (#164), Claude Opus 5: 79.2 (#1)
| Benchmark | Claude 3.5 Sonnet | Claude Opus 5 |
|---|---|---|
| LMArena Text | 1298 | 1507 |
| LMArena Creative Writing | 1292 | 1491 |
| EQ-Bench Creative Writing | 1451 | 2133 |
| LMArena Multi-Turn | 1326 | 1499 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| EQ-Bench 4 | — | 1385 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Claude Opus 5?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Claude Opus 5 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Claude Opus 5 share?
26 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude Opus 5 has 57.