Model comparison
Claude Opus 4.5 vs o3-pro
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 42.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. Claude Opus 4.5 scores higher in 3 categories and o3-pro in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4.5 leads 56.5 to 29.5.
- The biggest single-benchmark swing is ARC-AGI-2: 37.6% for Claude Opus 4.5 and 4.9% for o3-pro.
- Claude Opus 4.5 is cheaper at $5 / $25 per million input/output tokens, against $20 / $80 for o3-pro.
Side by side
| Claude Opus 4.5 | o3-pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.5 | 42.9 |
| Released | 2025-11-01 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $5 | $20 |
| Output $ / M tokens | $25 | $80 |
| Results tracked | 69 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4.5: 54.8 (#27), o3-pro: 55.5 (#24)
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| WeirdML | 63.7% | 58.2% |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | 76.8% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1494 | — |
| SWE-bench Multilingual | 70.7% | — |
| GSO | 26.5% | — |
| LMArena Coding | 1504 | — |
| ALE-Bench | 1,025 | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.5: 47.3 (#12), o3-pro: —
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| Terminal-Bench | 63.1% | — |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
| Vending-Bench 2 | 4,967 | — |
Reasoning Claude Opus 4.5 leads
Claude Opus 4.5: 42.6 (#51), o3-pro: 23.8 (#171)
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| ARC-AGI-2 | 37.6% | 4.9% |
| Kagi LLM Benchmark | 80.2% | 72.1% |
| ARC-AGI-1 | 80% | 59.3% |
| DTBench | 89.9% | 86.9% |
| LMCA | 44.5% | 38.5% |
| Epoch Capabilities Index | 150.09 | 147.42 |
| SimpleBench | 62% | — |
| NYT Connections (extended) | 52.5% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| LMArena Hard Prompts | 1476 | — |
| Mystery Game Puzzles | 22% | — |
| ForecastBench | 60.7 | — |
Math Not comparable
Claude Opus 4.5: 38.6 (#132), o3-pro: —
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 86.1% | — |
| ProofBench | 36% | — |
| LMArena Math | 1463 | — |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.5 leads
Claude Opus 4.5: 56.5 (#44), o3-pro: 29.5 (#238)
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 23.3% |
| GPQA Diamond | 86% | — |
| Humanity's Last Exam | 25.2% | — |
| SimpleQA Verified | 45.7% | — |
| Confabulations | — | 14.2% |
| LMArena Expert | 1487 | — |
Multimodal Not comparable
Claude Opus 4.5: 31.4 (#107), o3-pro: —
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |
Multilingual Not comparable
Claude Opus 4.5: 54.3 (#47), o3-pro: —
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| LMArena Non-English | 1438 | — |
| LMArena Chinese | 1470 | — |
| LMArena French | 1471 | — |
| LMArena German | 1449 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1424 | — |
| LMArena Russian | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following Not comparable
Claude Opus 4.5: 77.5 (#19), o3-pro: —
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1478 | — |
Long Context o3-pro leads
Claude Opus 4.5: 46.5 (#22), o3-pro: 72.2 (#1)
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| CL-bench | 21.1% | — |
| LMArena Longer Query | 1480 | — |
Writing & Preference Claude Opus 4.5 leads
Claude Opus 4.5: 68.1 (#28), o3-pro: 57.1 (#133)
| Benchmark | Claude Opus 4.5 | o3-pro |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1445 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1687 | — |
| LMArena Multi-Turn | 1466 | — |
Frequently asked questions
Is Claude Opus 4.5 better than o3-pro?
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 42.9 on the Noometry Index.
Which is cheaper, Claude Opus 4.5 or o3-pro?
Claude Opus 4.5 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; o3-pro lists at $20 and $80.
Is Claude Opus 4.5 or o3-pro better for coding?
They score almost the same on coding (54.8 vs 55.5); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Opus 4.5 and o3-pro share?
8 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and o3-pro has 12.