Model comparison
Mistral vs o1
o1 is the stronger model overall, scoring 40.6 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1 leads 41.5 to 16.3.
Side by side
| Mistral | o1 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 29.4 | 40.6 |
| Released | — | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 22 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Mistral: 33.2 (#249), o1: 45.7 (#64)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Coding | 1162 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Mistral: —, o1: 24.3 (#111)
| Benchmark | Mistral | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Mistral: 21.3 (#199), o1: 27.5 (#103)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1372 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.92 |
| LiveBench | — | 75.7% |
Math o1 leads
Mistral: 20.5 (#275), o1: 34.9 (#150)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Math | 1180 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| Omni-MATH | 7.2% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Mistral: 16.3 (#283), o1: 41.5 (#101)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Expert | 1125 | 1362 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 27.7% | — |
| Confabulations | — | 11.7% |
| GPQA (HELM) | 30.3% | — |
Multimodal Not comparable
Mistral: —, o1: 33.6 (#87)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Mistral: 33.0 (#249), o1: 48.8 (#137)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Non-English | 1129 | 1359 |
| LMArena Chinese | 1109 | 1394 |
| LMArena French | 1179 | 1343 |
| LMArena German | 1155 | 1337 |
| LMArena Japanese | 1012 | 1346 |
| LMArena Korean | 1032 | 1396 |
| LMArena Russian | 1168 | 1356 |
| LMArena Spanish | 1143 | 1345 |
Instruction Following o1 leads
Mistral: 52.9 (#283), o1: 75.0 (#82)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Instruction Following | 1152 | 1368 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 56.8% | — |
Long Context o1 leads
Mistral: 35.0 (#240), o1: 50.3 (#9)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Longer Query | 1154 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Mistral: 37.2 (#255), o1: 55.8 (#139)
| Benchmark | Mistral | o1 |
|---|---|---|
| LMArena Text | 1165 | 1366 |
| LMArena Creative Writing | 1158 | 1347 |
| LMArena Multi-Turn | 1147 | 1368 |
| Short-Story Creative Writing | — | 70.2% |
| WildBench | 66% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Mistral better than o1?
o1 is the stronger model overall, scoring 40.6 to 29.4 on the Noometry Index.
Is Mistral or o1 better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 33.2 in the Noometry coding category.
How many benchmarks do Mistral and o1 share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and o1 has 52.