Model comparison
Claude Sonnet 4 vs o4-mini
Claude Sonnet 4 and o4-mini score almost the same on the Noometry Index (40.8 vs 41.6), so choose on price, context window or the category you care about most.
Last verified . 51 shared benchmarks.
Summary
- They share 51 benchmarks with published results for both. Claude Sonnet 4 scores higher in 4 categories and o4-mini in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where o4-mini leads 40.2 to 26.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 46.9% for Claude Sonnet 4 and 77.8% for o4-mini.
- o4-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 | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 41.6 |
| Released | 2025-05-22 | 2025-04-16 |
| 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 | 60 |
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), o4-mini: 40.9 (#127)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 45% |
| Aider Polyglot | 61.3% | 72% |
| GSO | 4.9% | 3.6% |
| WeirdML | 46.1% | 52.6% |
| LMArena Coding | 1414 | 1368 |
| ALE-Bench | 655.35 | 826.17 |
| SciCode | 40% | — |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), o4-mini: 32.6 (#61)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| METR Time Horizons | 62% | 63.9% |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
Reasoning o4-mini leads
Claude Sonnet 4: 22.9 (#187), o4-mini: 24.6 (#162)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 5.9% | 6.1% |
| SimpleBench | 45.5% | 38.7% |
| Kagi LLM Benchmark | 73% | 67.6% |
| ARC-AGI-1 | 40% | 58.7% |
| CritPt | 0.3% | 0.6% |
| EnigmaEval | 3.1% | 9.2% |
| LMArena Hard Prompts | 1372 | 1351 |
| DTBench | 77.1% | 77.6% |
| LMCA | 29% | 26.5% |
| Epoch Capabilities Index | 141.69 | 145.64 |
| ForecastBench | 60.2 | 61.8 |
| Chess Puzzles | — | 26% |
| Mystery Game Puzzles | — | 5% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), o4-mini: 40.8 (#89)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 81.7% |
| Omni-MATH | 60.2% | 72% |
| LMArena Math | 1375 | 1389 |
| MATH Level 5 | 84.4% | 97.8% |
| FrontierMath (Feb 2025 set) | 4.1% | 24.8% |
| FrontierMath Tier 4 (v1) | 0% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
Knowledge o4-mini leads
Claude Sonnet 4: 41.8 (#108), o4-mini: 43.6 (#91)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| GPQA Diamond | 79.2% | 79.6% |
| Humanity's Last Exam | 7.8% | 18.1% |
| MMLU-Pro | 84.3% | 82% |
| Confabulations | 13.2% | 15.8% |
| Vectara Hallucination Rate | 10.3% | 18.6% |
| GPQA (HELM) | 70.6% | 73.5% |
| LMArena Expert | 1372 | 1343 |
| SimpleQA Verified | — | 19.6% |
Multimodal o4-mini leads
Claude Sonnet 4: 26.2 (#121), o4-mini: 40.2 (#49)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| LMArena Vision | 1191 | 1194 |
| GeoBench | 37% | 64% |
| VPCT | 34% | 57.5% |
| MindCube | 44.8% | — |
Multilingual Too close to call
Claude Sonnet 4: 46.7 (#156), o4-mini: 47.0 (#154)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| LMArena Non-English | 1333 | 1337 |
| LMArena Chinese | 1350 | 1354 |
| LMArena French | 1363 | 1364 |
| LMArena German | 1331 | 1336 |
| LMArena Japanese | 1302 | 1308 |
| LMArena Korean | 1291 | 1312 |
| LMArena Russian | 1355 | 1334 |
| LMArena Spanish | 1357 | 1347 |
Instruction Following o4-mini leads
Claude Sonnet 4: 71.7 (#145), o4-mini: 75.2 (#68)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| IFEval | 84% | 92.8% |
| LMArena Instruction Following | 1376 | 1321 |
Long Context o4-mini leads
Claude Sonnet 4: 33.7 (#259), o4-mini: 45.5 (#33)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| Fiction.LiveBench | 46.9% | 77.8% |
| LMArena Longer Query | 1398 | 1315 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), o4-mini: 54.0 (#152)
| Benchmark | Claude Sonnet 4 | o4-mini |
|---|---|---|
| LMArena Text | 1351 | 1353 |
| LMArena Creative Writing | 1345 | 1294 |
| Short-Story Creative Writing | 81.4% | 75% |
| WildBench | 83.8% | 85.4% |
| LMArena Multi-Turn | 1376 | 1350 |
| EQ-Bench Creative Writing | 1483 | — |
Frequently asked questions
Is Claude Sonnet 4 better than o4-mini?
Claude Sonnet 4 and o4-mini score almost the same on the Noometry Index (40.8 vs 41.6), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4 or o4-mini?
o4-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 o4-mini better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Sonnet 4 and o4-mini share?
51 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and o4-mini has 60.