Model comparison
Mistral Large 3 vs o3-mini
Mistral Large 3 is the stronger model overall, scoring 39.1 to 36.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 4 categories and o3-mini in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 28.1.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Mistral Large 3 accepts more context: 262K tokens versus 200K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 39.1 | 36.7 |
| Released | 2025-12-02 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.25 | $1.10 |
| Output $ / M tokens | $0.75 | $4.40 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Mistral Large 3: 34.4 (#237), o3-mini: 40.8 (#132)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Coding | 1448 | 1378 |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1230 | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, o3-mini: 29.6 (#84)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Mistral Large 3: 15.2 (#319), o3-mini: 16.3 (#305)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1366 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | 23% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.34 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Mistral Large 3 leads
Mistral Large 3: 38.7 (#129), o3-mini: 28.1 (#244)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Math | 1414 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Mistral Large 3: 36.0 (#177), o3-mini: 38.3 (#146)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Expert | 1421 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), o3-mini: —
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Mistral Large 3 leads
Mistral Large 3: 52.5 (#84), o3-mini: 45.7 (#164)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Non-English | 1413 | 1319 |
| LMArena Chinese | 1447 | 1379 |
| LMArena French | 1455 | 1334 |
| LMArena German | 1437 | 1303 |
| LMArena Japanese | 1394 | 1286 |
| LMArena Korean | 1384 | 1314 |
| LMArena Russian | 1411 | 1304 |
| LMArena Spanish | 1440 | 1321 |
Instruction Following o3-mini leads
Mistral Large 3: 74.0 (#108), o3-mini: 75.1 (#72)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1403 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Mistral Large 3 leads
Mistral Large 3: 43.1 (#105), o3-mini: 33.8 (#256)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1413 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.0 (#101), o3-mini: 50.3 (#182)
| Benchmark | Mistral Large 3 | o3-mini |
|---|---|---|
| LMArena Text | 1428 | 1337 |
| LMArena Creative Writing | 1386 | 1286 |
| LMArena Multi-Turn | 1429 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1412 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Mistral Large 3 better than o3-mini?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 36.7 on the Noometry Index.
Which is cheaper, Mistral Large 3 or o3-mini?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Mistral Large 3 or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 200K.
How many benchmarks do Mistral Large 3 and o3-mini share?
17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and o3-mini has 51.