Model comparison
Claude Opus 5 vs o1
Claude Opus 5 is the stronger model overall, scoring 67.8 to 40.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and o1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 85.6% for Claude Opus 5 and 14.7% for o1.
- Claude Opus 5 is cheaper at $5 / $25 per million input/output tokens, against $15 / $60 for o1.
- Claude Opus 5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Opus 5 | o1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 40.9 |
| Released | 2026-07-24 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $5 | $15 |
| Output $ / M tokens | $25 | $60 |
| Results tracked | 57 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), o1: 46.1 (#70)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| WeirdML | 91.8% | 47.6% |
| LMArena Coding | 1534 | 1367 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| Aider Polyglot | — | 61.7% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 2,165 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), o1: 24.6 (#117)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| Cybench | — | 10% |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), o1: 27.9 (#111)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| SimpleBench | 80.6% | 41.7% |
| ARC-AGI-1 | 97.5% | 30.7% |
| Chess Puzzles | 42% | 15% |
| LMArena Hard Prompts | 1526 | 1371 |
| DTBench | 97.9% | 74.7% |
| LMCA | 64.5% | 22.3% |
| Epoch Capabilities Index | 162.78 | 141.91 |
| ARC-AGI-2 | 90.4% | — |
| NYT Connections (extended) | 94.3% | — |
| CritPt | 29.1% | — |
| EnigmaEval | — | 5.7% |
| EBR-Bench | 45.7% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 59% | — |
| LiveBench Data Analysis | — | 65.5% |
| Bench to the Future 3 | 0.12 | — |
| LiveBench | — | 75.7% |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), o1: 36.1 (#175)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 14.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 73.3% |
| LMArena Math | 1531 | 1388 |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), o1: 41.5 (#110)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| GPQA Diamond | 93.9% | 76.8% |
| SimpleQA Verified | 59.9% | 41.1% |
| LMArena Expert | 1557 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), o1: 34.2 (#93)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| LMArena Vision | 1319 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), o1: 48.6 (#142)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| LMArena Non-English | 1501 | 1358 |
| LMArena Chinese | 1574 | 1394 |
| LMArena French | 1519 | 1344 |
| LMArena German | 1524 | 1337 |
| LMArena Japanese | 1516 | 1346 |
| LMArena Korean | 1521 | 1396 |
| LMArena Russian | 1507 | 1356 |
| LMArena Spanish | 1519 | 1345 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), o1: 74.8 (#86)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Claude Opus 5: 46.5 (#21), o1: 50.3 (#9)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| LMArena Longer Query | 1515 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), o1: 55.6 (#144)
| Benchmark | Claude Opus 5 | o1 |
|---|---|---|
| LMArena Text | 1507 | 1366 |
| LMArena Creative Writing | 1491 | 1348 |
| LMArena Multi-Turn | 1499 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Claude Opus 5 better than o1?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 40.9 on the Noometry Index.
Which is cheaper, Claude Opus 5 or o1?
Claude Opus 5 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; o1 lists at $15 and $60.
Is Claude Opus 5 or o1 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 5 and o1 share?
29 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and o1 has 52.