Model comparison
Mistral Large vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 31.9 on the Noometry Index.
Last verified . 37 shared benchmarks.
Mistral AISummary
- They share 37 benchmarks with published results for both. Mistral Large scores higher in 1 category and o3-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o3-mini leads 28.1 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 76.9% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- o3-mini accepts more context: 200K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 31.9 | 36.7 |
| Released | 2024-02-26 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 200K |
| Max output | 16K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $6 | $4.40 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Mistral Large: 34.3 (#240), o3-mini: 40.8 (#132)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| SciCode | 36.2% | 39.8% |
| LiveBench Coding | 47.1% | 82.7% |
| LMArena Coding | 1277 | 1378 |
| Aider Polyglot | — | 60.4% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 30% | — |
| BigCodeBench Complete | 38.3% | — |
| CadEval | — | 54% |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use o3-mini leads
Mistral Large: 28.6 (#89), o3-mini: 29.6 (#84)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
| Cybench | — | 22.5% |
Reasoning Too close to call
Mistral Large: 15.8 (#310), o3-mini: 16.3 (#305)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| SimpleBench | 22.5% | 22.8% |
| CritPt | 0% | 0.3% |
| LiveBench Reasoning | 43.5% | 89.6% |
| LMArena Hard Prompts | 1257 | 1366 |
| DTBench | 65.1% | 68.8% |
| LiveBench Data Analysis | 50.1% | 70.6% |
| LMCA | 16.7% | 19% |
| Epoch Capabilities Index | 128.52 | 140.34 |
| ForecastBench | 57.1 | 59.6 |
| LiveBench | 48.4% | 75.9% |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
Math o3-mini leads
Mistral Large: 18.2 (#291), o3-mini: 28.1 (#244)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 76.9% |
| LiveBench Math | 42.5% | 77.3% |
| LMArena Math | 1262 | 1396 |
| MATH Level 5 | 50.3% | 96.5% |
| FrontierMath (Feb 2025 set) | 0.3% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 28.1% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Mistral Large: 30.1 (#230), o3-mini: 38.3 (#146)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| GPQA Diamond | 51.3% | 77% |
| Confabulations | 21.4% | 17.9% |
| LMArena Expert | 1232 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 59.9% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual o3-mini leads
Mistral Large: 40.0 (#219), o3-mini: 45.7 (#164)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| LMArena Non-English | 1237 | 1319 |
| LMArena Chinese | 1240 | 1379 |
| LMArena French | 1325 | 1334 |
| LMArena German | 1254 | 1303 |
| LMArena Japanese | 1188 | 1286 |
| LMArena Korean | 1202 | 1314 |
| LMArena Russian | 1257 | 1304 |
| LMArena Spanish | 1268 | 1321 |
Instruction Following o3-mini leads
Mistral Large: 67.9 (#191), o3-mini: 75.1 (#72)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 84.4% |
| LMArena Instruction Following | 1249 | 1337 |
| IFEval | 87.7% | — |
Long Context Mistral Large leads
Mistral Large: 38.3 (#199), o3-mini: 33.8 (#256)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| LMArena Longer Query | 1261 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Mistral Large: 40.7 (#242), o3-mini: 50.3 (#182)
| Benchmark | Mistral Large | o3-mini |
|---|---|---|
| LMArena Text | 1266 | 1337 |
| LMArena Creative Writing | 1243 | 1286 |
| Short-Story Creative Writing | 69% | 61.7% |
| LMArena Multi-Turn | 1260 | 1320 |
| LiveBench Language | 39.4% | 50.7% |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
Frequently asked questions
Is Mistral Large better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 131K.
How many benchmarks do Mistral Large and o3-mini share?
37 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and o3-mini has 51.