Model comparison
Claude Sonnet 4.5 vs o1-mini
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 33.7 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and o1-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.7 to 48.6.
- The biggest single-benchmark swing is Cybench: 60% for Claude Sonnet 4.5 and 10% for o1-mini.
Side by side
| Claude Sonnet 4.5 | o1-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 44.0 | 33.7 |
| Released | 2025-09-29 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 73 | 39 |
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: 47.8 (#54), o1-mini: 35.1 (#218)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| WeirdML | 47.7% | 36.3% |
| LMArena Coding | 1489 | 1362 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.1 (#30), o1-mini: 24.3 (#112)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| Cybench | 60% | 10% |
| 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 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 26.9 (#113), o1-mini: 8.9 (#340)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 13.6% | 0.8% |
| SimpleBench | 54.3% | 18.1% |
| ARC-AGI-1 | 63.7% | 14% |
| LMArena Hard Prompts | 1462 | 1333 |
| Epoch Capabilities Index | 146.84 | 135.82 |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 38.8% | — |
| ForecastBench | 61.9 | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
Claude Sonnet 4.5: 31.9 (#190), o1-mini: 33.7 (#168)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 46.9% |
| LMArena Math | 1448 | 1358 |
| MATH Level 5 | 97.7% | 89.2% |
| FrontierMath (Feb 2025 set) | 15.2% | 1.7% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#70), o1-mini: 34.8 (#180)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| GPQA Diamond | 82.3% | 62.4% |
| LMArena Expert | 1483 | 1316 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.1 (#84), o1-mini: —
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.6 (#65), o1-mini: 43.8 (#177)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| LMArena Non-English | 1425 | 1289 |
| LMArena Chinese | 1459 | 1314 |
| LMArena French | 1459 | 1292 |
| LMArena German | 1427 | 1278 |
| LMArena Japanese | 1390 | 1245 |
| LMArena Korean | 1403 | 1223 |
| LMArena Russian | 1436 | 1283 |
| LMArena Spanish | 1457 | 1302 |
Instruction Following Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 75.2 (#74), o1-mini: 67.0 (#200)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1459 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#45), o1-mini: 40.1 (#156)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1476 | 1321 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.7 (#33), o1-mini: 48.6 (#196)
| Benchmark | Claude Sonnet 4.5 | o1-mini |
|---|---|---|
| LMArena Text | 1439 | 1317 |
| LMArena Creative Writing | 1442 | 1244 |
| LMArena Multi-Turn | 1465 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Claude Sonnet 4.5 better than o1-mini?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 33.7 on the Noometry Index.
Is Claude Sonnet 4.5 or o1-mini better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 35.1 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4.5 and o1-mini share?
27 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and o1-mini has 39.