Model comparison
Claude Opus 4.1 vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 41.0 on the Noometry Index.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude Opus 4.1 scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 44.5.
- The biggest single-benchmark swing is WeirdML: 45.9% for Claude Opus 4.1 and 58.2% for o3-pro.
- Claude Opus 4.1 is cheaper at $15 / $75 per million input/output tokens, against $20 / $80 for o3-pro.
Side by side
| Claude Opus 4.1 | o3-pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 42.9 |
| Released | 2025-08-05 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 32K | 100K |
| Input $ / M tokens | $15 | $20 |
| Output $ / M tokens | $75 | $80 |
| Results tracked | 48 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Claude Opus 4.1: 44.4 (#73), o3-pro: 55.5 (#24)
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| WeirdML | 45.9% | 58.2% |
| SWE-bench Verified | 73.3% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1390 | — |
| LMArena Coding | 1479 | — |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.1: 35.0 (#41), o3-pro: —
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), o3-pro: 23.8 (#171)
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| DTBench | 80% | 86.9% |
| LMCA | 37.1% | 38.5% |
| Epoch Capabilities Index | 144.12 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| LMArena Hard Prompts | 1443 | — |
| Mystery Game Puzzles | 21% | — |
| ForecastBench | 62 | — |
Math Not comparable
Claude Opus 4.1: 22.3 (#277), o3-pro: —
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.9% | — |
| LMArena Math | 1431 | — |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 42.0 (#101), o3-pro: 29.5 (#238)
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| Confabulations | 17.1% | 14.2% |
| Vectara Hallucination Rate | 11.8% | 23.3% |
| GPQA Diamond | 77.3% | — |
| Humanity's Last Exam | 11.5% | — |
| LMArena Expert | 1439 | — |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), o3-pro: —
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| VPCT | 35% | — |
Multilingual Not comparable
Claude Opus 4.1: 52.0 (#95), o3-pro: —
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| LMArena Non-English | 1405 | — |
| LMArena Chinese | 1427 | — |
| LMArena French | 1431 | — |
| LMArena German | 1413 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1422 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Claude Opus 4.1: 75.6 (#58), o3-pro: —
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1435 | — |
Long Context o3-pro leads
Claude Opus 4.1: 44.5 (#63), o3-pro: 72.2 (#1)
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1455 | — |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), o3-pro: 57.1 (#133)
| Benchmark | Claude Opus 4.1 | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 84.7% | 84.4% |
| LMArena Text | 1419 | — |
| LMArena Creative Writing | 1412 | — |
| LMArena Multi-Turn | 1444 | — |
Frequently asked questions
Is Claude Opus 4.1 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or o3-pro?
Claude Opus 4.1 is cheaper. It lists at $15 per million input tokens and $75 per million output tokens; o3-pro lists at $20 and $80.
Is Claude Opus 4.1 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 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-pro share?
7 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and o3-pro has 12.