Model comparison
Claude Opus 4 vs o1
Claude Opus 4 is the stronger model overall, scoring 43.1 to 40.9 on the Noometry Index.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and o1 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 39.6.
- The biggest single-benchmark swing is GeoBench: 49% for Claude Opus 4 and 80% for o1.
- o1 is cheaper at $15 / $60 per million input/output tokens, against $15 / $75 for Claude Opus 4.
Side by side
| Claude Opus 4 | o1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 40.9 |
| Released | 2025-05-22 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 32K | 100K |
| Input $ / M tokens | $15 | $15 |
| Output $ / M tokens | $75 | $60 |
| Results tracked | 56 | 52 |
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: 46.1 (#70)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| Aider Polyglot | 72% | 61.7% |
| WeirdML | 43.7% | 47.6% |
| LMArena Coding | 1442 | 1367 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| GSO | 6.9% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| AlgoTune | 1.33 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), o1: 24.6 (#117)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| Cybench | 38% | 10% |
| METR Time Horizons | 63.9% | 51.1% |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
Reasoning Too close to call
Claude Opus 4: 27.3 (#121), o1: 27.9 (#111)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| SimpleBench | 58.8% | 41.7% |
| ARC-AGI-1 | 35.7% | 30.7% |
| EnigmaEval | 5.6% | 5.7% |
| LMArena Hard Prompts | 1399 | 1371 |
| DTBench | 81.6% | 74.7% |
| LMCA | 37.4% | 22.3% |
| Epoch Capabilities Index | 142.67 | 141.91 |
| ARC-AGI-2 | 8.6% | — |
| Kagi LLM Benchmark | 74.3% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 15% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 61.1 | — |
| LiveBench | — | 75.7% |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), o1: 36.1 (#175)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 73.3% |
| LMArena Math | 1390 | 1388 |
| MATH Level 5 | 85% | 94.7% |
| FrontierMath (Feb 2025 set) | 4.5% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 61.6% | — |
| LiveBench Math | — | 80.3% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), o1: 41.5 (#110)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| GPQA Diamond | 76.3% | 76.8% |
| Humanity's Last Exam | 10.7% | 8% |
| Confabulations | 15.9% | 11.7% |
| LMArena Expert | 1386 | 1361 |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 87.5% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal o1 leads
Claude Opus 4: 31.5 (#106), o1: 34.2 (#93)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| LMArena Vision | 1192 | 1168 |
| GeoBench | 49% | 80% |
| VPCT | 38% | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Too close to call
Claude Opus 4: 48.8 (#138), o1: 48.6 (#142)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| LMArena Non-English | 1362 | 1358 |
| LMArena Chinese | 1386 | 1394 |
| LMArena French | 1372 | 1344 |
| LMArena German | 1391 | 1337 |
| LMArena Japanese | 1331 | 1346 |
| LMArena Korean | 1321 | 1396 |
| LMArena Russian | 1392 | 1356 |
| LMArena Spanish | 1389 | 1345 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), o1: 74.8 (#86)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 91.8% | — |
Long Context o1 leads
Claude Opus 4: 39.6 (#172), o1: 50.3 (#9)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 83.3% |
| LMArena Longer Query | 1422 | 1378 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), o1: 55.6 (#144)
| Benchmark | Claude Opus 4 | o1 |
|---|---|---|
| LMArena Text | 1377 | 1366 |
| LMArena Creative Writing | 1387 | 1348 |
| Short-Story Creative Writing | 83.6% | 70.2% |
| LMArena Multi-Turn | 1396 | 1369 |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Claude Opus 4 better than o1?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 40.9 on the Noometry Index.
Which is cheaper, Claude Opus 4 or o1?
o1 is cheaper. It lists at $15 per million input tokens and $60 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or o1 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Opus 4 and o1 share?
38 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and o1 has 52.