Model comparison
Claude Opus 4.1 vs o3
o3 is the stronger model overall, scoring 47.5 to 41.0 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Opus 4.1 scores higher in 4 categories and o3 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where o3 leads 50.2 to 22.3.
- The biggest single-benchmark swing is Chess Puzzles: 7% for Claude Opus 4.1 and 38% for o3.
- o3 is cheaper at $2 / $8 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
Side by side
| Claude Opus 4.1 | o3 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 47.5 |
| Released | 2025-08-05 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 32K | 100K |
| Input $ / M tokens | $15 | $2 |
| Output $ / M tokens | $75 | $8 |
| Results tracked | 48 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Claude Opus 4.1: 44.4 (#73), o3: 46.8 (#64)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| SWE-bench Verified | 73.3% | 62.3% |
| WeirdML | 45.9% | 52.4% |
| LMArena Coding | 1479 | 1408 |
| ALE-Bench | 674.77 | 933.55 |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1390 | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Too close to call
Claude Opus 4.1: 35.0 (#41), o3: 34.5 (#44)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| GDPval | 43.6% | 30.8% |
| DeepResearch Bench | 48.3% | 45.2% |
| LMArena Search | 1148 | 1144 |
| METR Time Horizons | 66.8% | 65.4% |
| Terminal-Bench | 38% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| Cybench | 42% | — |
| OSWorld | — | 23% |
Reasoning Too close to call
Claude Opus 4.1: 32.2 (#76), o3: 32.0 (#78)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| SimpleBench | 60% | 53.1% |
| Chess Puzzles | 7% | 38% |
| EnigmaEval | 7.2% | 13.1% |
| LMArena Hard Prompts | 1443 | 1402 |
| Mystery Game Puzzles | 21% | 29% |
| DTBench | 80% | 84.8% |
| LMCA | 37.1% | 39.7% |
| Epoch Capabilities Index | 144.12 | 146.86 |
| ForecastBench | 62 | 62.5 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| EBR-Bench | 7.9% | — |
Math o3 leads
Claude Opus 4.1: 22.3 (#277), o3: 50.2 (#58)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 33.3% |
| OTIS Mock AIME 2024-2025 | 68.9% | 84.4% |
| LMArena Math | 1431 | 1426 |
| FrontierMath (Feb 2025 set) | 7.2% | 18.7% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| FrontierMath Tier 4 | 2.4% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
Knowledge o3 leads
Claude Opus 4.1: 42.0 (#101), o3: 54.6 (#52)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| GPQA Diamond | 77.3% | 81.8% |
| Humanity's Last Exam | 11.5% | 20.3% |
| Confabulations | 17.1% | 14.4% |
| LMArena Expert | 1439 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Vectara Hallucination Rate | 11.8% | — |
| GPQA (HELM) | — | 75.3% |
Multimodal o3 leads
Claude Opus 4.1: 26.8 (#119), o3: 41.4 (#36)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| VPCT | 35% | 52% |
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
Multilingual Too close to call
Claude Opus 4.1: 52.0 (#95), o3: 51.7 (#105)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| LMArena Non-English | 1405 | 1401 |
| LMArena Chinese | 1427 | 1437 |
| LMArena French | 1431 | 1430 |
| LMArena German | 1413 | 1420 |
| LMArena Japanese | 1378 | 1403 |
| LMArena Korean | 1380 | 1370 |
| LMArena Russian | 1422 | 1406 |
| LMArena Spanish | 1448 | 1395 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), o3: 72.8 (#127)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Claude Opus 4.1: 44.5 (#63), o3: 53.3 (#6)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Claude Opus 4.1: 62.4 (#74), o3: 63.5 (#64)
| Benchmark | Claude Opus 4.1 | o3 |
|---|---|---|
| LMArena Text | 1419 | 1410 |
| LMArena Creative Writing | 1412 | 1359 |
| Short-Story Creative Writing | 84.7% | 83.9% |
| LMArena Multi-Turn | 1444 | 1405 |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Claude Opus 4.1 better than o3?
o3 is the stronger model overall, scoring 47.5 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or o3?
o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 44.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Opus 4.1 and o3 share?
41 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and o3 has 63.