Up to four models
Claude Opus 4.1 vs Claude Opus 4
On the index (GPT-4 = 100), Claude Opus 4.1 scores 140 and Claude Opus 4 136. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Opus 4.1
140124–156
WeightsClosed
ReleasedAug 2025
Price in / out$15 / $75
Context200K
Core tests taken5 of 9
Claude Opus 4.1 and Claude Opus 4 are too close to call (4 points apart, within the uncertainty), ahead on 4 of 4 shared core tests.
Test by testthird-party results
Claude Opus 4.1Claude Opus 4
Every result as a table
| Test | Claude Opus 4.1 | Claude Opus 4 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 77.3% | 76.3% |
| Humanity's Last Exam | 11.5% | 10.7% |
| GPQA Diamond (Vals AI) | 76.3% | 71.7% |
| MMLU Pro | 87.9% | 86.2% |
| MMMU Pro | 77.5% | 73.3% |
| SimpleBench | 60.0% | 58.8% |
| VPCT | 35.0% | 38.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 68.9% | 64.4% |
| MATH 500 | 95.4% | 90.4% |
| MGSM | 94.4% | 93.8% |
| FrontierMath (2025 set) | 7.2% | 4.5% |
| FrontierMath tier 4 (2025 set) | 4.2% | 4.2% |
| Coding | ||
| SWE-bench Verified | 73.4% | 70.7% |
| LiveCodeBench | 66.5% | 70.2% |
| WeirdML | 45.9% | 43.7% |
| Agents | ||
| DTBench | 80.0% | 81.6% |
| DeepResearch Bench | 48.3% | 46.8% |
| LMCA | 37.1% | 37.4% |
| Professional work | ||
| LegalBench | 83.5% | 83.1% |
| MortgageTax | 61.1% | 58.6% |
| TaxEval v2 | 73.7% | 71.9% |
Task length · METR40 sec38 sec
Tests at least two of these models have taken. Bold rows are the core tests.