Model comparison
Mistral Large vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 31.9 on the Noometry Index.
Last verified . 34 shared benchmarks.
Mistral AISummary
- They share 34 benchmarks with published results for both. Mistral Large scores higher in 3 categories and o1-mini in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 18.2.
- The biggest single-benchmark swing is MATH Level 5: 50.3% for Mistral Large and 89.2% for o1-mini.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | o1-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.9 | 34.0 |
| Released | 2024-02-26 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Mistral Large: 34.3 (#240), o1-mini: 35.5 (#224)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| LiveBench Coding | 47.1% | 48% |
| LMArena Coding | 1277 | 1362 |
| HumanEval+ | 62.2% | 89% |
| MBPP+ | 59.5% | 78.8% |
| Aider Polyglot | — | 32.9% |
| SciCode | 36.2% | — |
| WeirdML | — | 36.3% |
| BigCodeBench Instruct | 30% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
Agentic & Tool Use Mistral Large leads
Mistral Large: 28.6 (#89), o1-mini: 24.6 (#118)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
| Cybench | — | 10% |
Reasoning Mistral Large leads
Mistral Large: 15.8 (#310), o1-mini: 8.8 (#346)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| SimpleBench | 22.5% | 18.1% |
| LiveBench Reasoning | 43.5% | 72.3% |
| LMArena Hard Prompts | 1257 | 1333 |
| LiveBench Data Analysis | 50.1% | 57.9% |
| Epoch Capabilities Index | 128.52 | 135.82 |
| LiveBench | 48.4% | 57.8% |
| ARC-AGI-2 | — | 0.8% |
| ARC-AGI-1 | — | 14% |
| CritPt | 0% | — |
| DTBench | 65.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |
Math o1-mini leads
Mistral Large: 18.2 (#291), o1-mini: 35.4 (#186)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 46.9% |
| LiveBench Math | 42.5% | 62% |
| LMArena Math | 1262 | 1358 |
| MATH Level 5 | 50.3% | 89.2% |
| FrontierMath (Feb 2025 set) | 0.3% | 1.7% |
| Omni-MATH | 28.1% | — |
Knowledge o1-mini leads
Mistral Large: 30.1 (#230), o1-mini: 34.9 (#192)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| GPQA Diamond | 51.3% | 62.4% |
| Confabulations | 21.4% | 18.6% |
| LMArena Expert | 1232 | 1316 |
| MMLU-Pro | 59.9% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual o1-mini leads
Mistral Large: 40.0 (#219), o1-mini: 43.6 (#182)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| LMArena Non-English | 1237 | 1289 |
| LMArena Chinese | 1240 | 1314 |
| LMArena French | 1325 | 1293 |
| LMArena German | 1254 | 1278 |
| LMArena Japanese | 1188 | 1245 |
| LMArena Korean | 1202 | 1223 |
| LMArena Russian | 1257 | 1283 |
| LMArena Spanish | 1268 | 1303 |
Instruction Following Mistral Large leads
Mistral Large: 67.9 (#191), o1-mini: 66.7 (#206)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 65.4% |
| LMArena Instruction Following | 1249 | 1304 |
| IFEval | 87.7% | — |
Long Context o1-mini leads
Mistral Large: 38.3 (#199), o1-mini: 40.1 (#161)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| LMArena Longer Query | 1261 | 1320 |
Writing & Preference o1-mini leads
Mistral Large: 40.7 (#242), o1-mini: 48.4 (#202)
| Benchmark | Mistral Large | o1-mini |
|---|---|---|
| LMArena Text | 1266 | 1317 |
| LMArena Creative Writing | 1243 | 1244 |
| Short-Story Creative Writing | 69% | 64.9% |
| LMArena Multi-Turn | 1260 | 1314 |
| LiveBench Language | 39.4% | 40.9% |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
Frequently asked questions
Is Mistral Large better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 31.9 on the Noometry Index.
Is Mistral Large or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 34.3 in the Noometry coding category.
How many benchmarks do Mistral Large and o1-mini share?
34 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and o1-mini has 39.