Model comparison
Claude Opus 4 vs o1-mini
Claude Opus 4 is the stronger model overall, scoring 43.1 to 34.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Claude Opus 4 scores higher in 8 categories and o1-mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4 leads 27.3 to 8.8.
- The biggest single-benchmark swing is SimpleBench: 58.8% for Claude Opus 4 and 18.1% for o1-mini.
Side by side
| Claude Opus 4 | o1-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 34.0 |
| Released | 2025-05-22 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 32K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $75 | — |
| Results tracked | 56 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), o1-mini: 35.5 (#224)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| Aider Polyglot | 72% | 32.9% |
| WeirdML | 43.7% | 36.3% |
| LMArena Coding | 1442 | 1362 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| GSO | 6.9% | — |
| LiveBench Coding | — | 48% |
| AlgoTune | 1.33 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), o1-mini: 24.6 (#118)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| Cybench | 38% | 10% |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), o1-mini: 8.8 (#346)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 8.6% | 0.8% |
| SimpleBench | 58.8% | 18.1% |
| ARC-AGI-1 | 35.7% | 14% |
| LMArena Hard Prompts | 1399 | 1333 |
| Epoch Capabilities Index | 142.67 | 135.82 |
| Kagi LLM Benchmark | 74.3% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 81.6% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 37.4% | — |
| ForecastBench | 61.1 | — |
| LiveBench | — | 57.8% |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), o1-mini: 35.4 (#186)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 46.9% |
| LMArena Math | 1390 | 1358 |
| MATH Level 5 | 85% | 89.2% |
| FrontierMath (Feb 2025 set) | 4.5% | 1.7% |
| Omni-MATH | 61.6% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), o1-mini: 34.9 (#192)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| GPQA Diamond | 76.3% | 62.4% |
| Confabulations | 15.9% | 18.6% |
| LMArena Expert | 1386 | 1316 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), o1-mini: —
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Claude Opus 4 leads
Claude Opus 4: 48.8 (#138), o1-mini: 43.6 (#182)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| LMArena Non-English | 1362 | 1289 |
| LMArena Chinese | 1386 | 1314 |
| LMArena French | 1372 | 1293 |
| LMArena German | 1391 | 1278 |
| LMArena Japanese | 1331 | 1245 |
| LMArena Korean | 1321 | 1223 |
| LMArena Russian | 1392 | 1283 |
| LMArena Spanish | 1389 | 1303 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), o1-mini: 66.7 (#206)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1406 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 91.8% | — |
Long Context Too close to call
Claude Opus 4: 39.6 (#172), o1-mini: 40.1 (#161)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1422 | 1320 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), o1-mini: 48.4 (#202)
| Benchmark | Claude Opus 4 | o1-mini |
|---|---|---|
| LMArena Text | 1377 | 1317 |
| LMArena Creative Writing | 1387 | 1244 |
| Short-Story Creative Writing | 83.6% | 64.9% |
| LMArena Multi-Turn | 1396 | 1314 |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Claude Opus 4 better than o1-mini?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 34.0 on the Noometry Index.
Is Claude Opus 4 or o1-mini better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 35.5 in the Noometry coding category.
How many benchmarks do Claude Opus 4 and o1-mini share?
30 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and o1-mini has 39.