Model comparison
Claude Sonnet 4.5 vs o1
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 40.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 7 categories and o1 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 24.6.
- The biggest single-benchmark swing is Cybench: 60% for Claude Sonnet 4.5 and 10% for o1.
- Claude Sonnet 4.5 is cheaper at $3 / $15 per million input/output tokens, against $15 / $60 for o1.
Side by side
| Claude Sonnet 4.5 | o1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 44.1 | 40.9 |
| Released | 2025-09-29 | 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 | 73 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), o1: 46.1 (#70)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| WeirdML | 47.7% | 47.6% |
| LMArena Coding | 1489 | 1367 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), o1: 24.6 (#117)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| Cybench | 60% | 10% |
| METR Time Horizons | 67.4% | 51.1% |
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Too close to call
Claude Sonnet 4.5: 26.9 (#125), o1: 27.9 (#111)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| SimpleBench | 54.3% | 41.7% |
| ARC-AGI-1 | 63.7% | 30.7% |
| Chess Puzzles | 12% | 15% |
| EnigmaEval | 6% | 5.7% |
| LMArena Hard Prompts | 1462 | 1371 |
| DTBench | 83.2% | 74.7% |
| LMCA | 38.8% | 22.3% |
| Epoch Capabilities Index | 146.84 | 141.91 |
| ARC-AGI-2 | 13.6% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| CritPt | 1.1% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 17% | — |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 61.9 | — |
| LiveBench | — | 75.7% |
Math o1 leads
Claude Sonnet 4.5: 32.3 (#216), o1: 36.1 (#175)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 14.7% |
| OTIS Mock AIME 2024-2025 | 77.8% | 73.3% |
| LMArena Math | 1449 | 1388 |
| MATH Level 5 | 97.7% | 94.7% |
| FrontierMath (Feb 2025 set) | 15.2% | 9.3% |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| LiveBench Math | — | 80.3% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), o1: 41.5 (#110)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| GPQA Diamond | 82.3% | 76.8% |
| Humanity's Last Exam | 13.7% | 8% |
| SimpleQA Verified | 30.7% | 41.1% |
| LMArena Expert | 1482 | 1361 |
| MMLU-Pro | 86.9% | — |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Too close to call
Claude Sonnet 4.5: 34.8 (#89), o1: 34.2 (#93)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| VPCT | 39.8% | 37% |
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| LMArena Document | 1450 | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), o1: 48.6 (#142)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| LMArena Non-English | 1425 | 1358 |
| LMArena Chinese | 1459 | 1394 |
| LMArena French | 1458 | 1344 |
| LMArena German | 1427 | 1337 |
| LMArena Japanese | 1390 | 1346 |
| LMArena Korean | 1403 | 1396 |
| LMArena Russian | 1437 | 1356 |
| LMArena Spanish | 1457 | 1345 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), o1: 74.8 (#86)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 85% | — |
Long Context o1 leads
Claude Sonnet 4.5: 45.2 (#46), o1: 50.3 (#9)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| LMArena Longer Query | 1476 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), o1: 55.6 (#144)
| Benchmark | Claude Sonnet 4.5 | o1 |
|---|---|---|
| LMArena Text | 1439 | 1366 |
| LMArena Creative Writing | 1442 | 1348 |
| LMArena Multi-Turn | 1465 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Claude Sonnet 4.5 better than o1?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 40.9 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.5 or o1?
Claude Sonnet 4.5 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 4.5 or o1 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Sonnet 4.5 and o1 share?
35 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and o1 has 52.