Model comparison
Claude Sonnet 4 vs o1
Claude Sonnet 4 and o1 score almost the same on the Noometry Index (40.8 vs 40.9), so choose on price, context window or the category you care about most.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Sonnet 4 scores higher in 4 categories and o1 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 33.7.
- The biggest single-benchmark swing is GeoBench: 37% for Claude Sonnet 4 and 80% for o1.
- Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $15 / $60 for o1.
Side by side
| Claude Sonnet 4 | o1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 40.9 |
| Released | 2025-05-22 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $3 | $15 |
| Output $ / M tokens | $15 | $60 |
| Results tracked | 58 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Claude Sonnet 4: 43.5 (#88), o1: 46.1 (#70)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| Aider Polyglot | 61.3% | 61.7% |
| WeirdML | 46.1% | 47.6% |
| LMArena Coding | 1414 | 1367 |
| SWE-bench Verified (bash only) | 64.9% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 655.35 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), o1: 24.6 (#117)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| Cybench | 35% | 10% |
| METR Time Horizons | 62% | 51.1% |
| TheAgentCompany | 33.1% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
Reasoning o1 leads
Claude Sonnet 4: 22.9 (#187), o1: 27.9 (#111)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| SimpleBench | 45.5% | 41.7% |
| ARC-AGI-1 | 40% | 30.7% |
| EnigmaEval | 3.1% | 5.7% |
| LMArena Hard Prompts | 1372 | 1371 |
| DTBench | 77.1% | 74.7% |
| LMCA | 29% | 22.3% |
| Epoch Capabilities Index | 141.69 | 141.91 |
| ARC-AGI-2 | 5.9% | — |
| Kagi LLM Benchmark | 73% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 15% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 60.2 | — |
| LiveBench | — | 75.7% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), o1: 36.1 (#175)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 73.3% |
| LMArena Math | 1375 | 1388 |
| MATH Level 5 | 84.4% | 94.7% |
| FrontierMath (Feb 2025 set) | 4.1% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 80.3% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
Claude Sonnet 4: 41.8 (#108), o1: 41.5 (#110)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| GPQA Diamond | 79.2% | 76.8% |
| Humanity's Last Exam | 7.8% | 8% |
| Confabulations | 13.2% | 11.7% |
| LMArena Expert | 1372 | 1361 |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal o1 leads
Claude Sonnet 4: 26.2 (#121), o1: 34.2 (#93)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| LMArena Vision | 1191 | 1168 |
| GeoBench | 37% | 80% |
| VPCT | 34% | 37% |
| MindCube | 44.8% | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Claude Sonnet 4: 46.7 (#156), o1: 48.6 (#142)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| LMArena Non-English | 1333 | 1358 |
| LMArena Chinese | 1350 | 1394 |
| LMArena French | 1363 | 1344 |
| LMArena German | 1331 | 1337 |
| LMArena Japanese | 1302 | 1346 |
| LMArena Korean | 1291 | 1396 |
| LMArena Russian | 1355 | 1356 |
| LMArena Spanish | 1357 | 1345 |
Instruction Following o1 leads
Claude Sonnet 4: 71.7 (#145), o1: 74.8 (#86)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 84% | — |
Long Context o1 leads
Claude Sonnet 4: 33.7 (#259), o1: 50.3 (#9)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| Fiction.LiveBench | 46.9% | 83.3% |
| LMArena Longer Query | 1398 | 1378 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), o1: 55.6 (#144)
| Benchmark | Claude Sonnet 4 | o1 |
|---|---|---|
| LMArena Text | 1351 | 1366 |
| LMArena Creative Writing | 1345 | 1348 |
| Short-Story Creative Writing | 81.4% | 70.2% |
| LMArena Multi-Turn | 1376 | 1369 |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Claude Sonnet 4 better than o1?
Claude Sonnet 4 and o1 score almost the same on the Noometry Index (40.8 vs 40.9), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4 or o1?
Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; o1 lists at $15 and $60.
Is Claude Sonnet 4 or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 43.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Sonnet 4 and o1 share?
38 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and o1 has 52.