Model comparison
Claude Sonnet 4 vs o3-mini
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.7 on the Noometry Index. o3-mini costs 3.1× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and o3-mini in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 28.1.
- The biggest single-benchmark swing is SimpleBench: 45.5% for Claude Sonnet 4 and 22.8% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
Side by side
| Claude Sonnet 4 | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 36.7 |
| Released | 2025-05-22 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $3 | $1.10 |
| Output $ / M tokens | $15 | $4.40 |
| Results tracked | 58 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), o3-mini: 40.8 (#132)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| Aider Polyglot | 61.3% | 60.4% |
| SciCode | 40% | 39.8% |
| GSO | 4.9% | 1.3% |
| WeirdML | 46.1% | 43.7% |
| LMArena Coding | 1414 | 1378 |
| SWE-bench Verified (bash only) | 64.9% | — |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), o3-mini: 29.6 (#84)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| Cybench | 35% | 22.5% |
| TheAgentCompany | 33.1% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), o3-mini: 16.3 (#305)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 5.9% | 3% |
| SimpleBench | 45.5% | 22.8% |
| ARC-AGI-1 | 40% | 34.5% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1372 | 1366 |
| DTBench | 77.1% | 68.8% |
| LMCA | 29% | 19% |
| Epoch Capabilities Index | 141.69 | 140.34 |
| ForecastBench | 60.2 | 59.6 |
| Kagi LLM Benchmark | 73% | — |
| Chess Puzzles | — | 17% |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), o3-mini: 28.1 (#244)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 76.9% |
| LMArena Math | 1375 | 1396 |
| MATH Level 5 | 84.4% | 96.5% |
| FrontierMath (Feb 2025 set) | 4.1% | 12.4% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 77.3% |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), o3-mini: 38.3 (#146)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| GPQA Diamond | 79.2% | 77% |
| Confabulations | 13.2% | 17.9% |
| LMArena Expert | 1372 | 1364 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 84.3% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), o3-mini: —
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Too close to call
Claude Sonnet 4: 46.7 (#156), o3-mini: 45.7 (#164)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| LMArena Non-English | 1333 | 1319 |
| LMArena Chinese | 1350 | 1379 |
| LMArena French | 1363 | 1334 |
| LMArena German | 1331 | 1303 |
| LMArena Japanese | 1302 | 1286 |
| LMArena Korean | 1291 | 1314 |
| LMArena Russian | 1355 | 1304 |
| LMArena Spanish | 1357 | 1321 |
Instruction Following o3-mini leads
Claude Sonnet 4: 71.7 (#145), o3-mini: 75.1 (#72)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1376 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 84% | — |
Long Context Too close to call
Claude Sonnet 4: 33.7 (#259), o3-mini: 33.8 (#256)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| Fiction.LiveBench | 46.9% | 50% |
| LMArena Longer Query | 1398 | 1343 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), o3-mini: 50.3 (#182)
| Benchmark | Claude Sonnet 4 | o3-mini |
|---|---|---|
| LMArena Text | 1351 | 1337 |
| LMArena Creative Writing | 1345 | 1286 |
| Short-Story Creative Writing | 81.4% | 61.7% |
| LMArena Multi-Turn | 1376 | 1320 |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Claude Sonnet 4 better than o3-mini?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.7 on the Noometry Index. o3-mini costs 3.1× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or o3-mini better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Sonnet 4 and o3-mini share?
38 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and o3-mini has 51.