Model comparison
Mistral Medium vs o3
o3 is the stronger model overall, scoring 47.5 to 36.3 on the Noometry Index.
Last verified . 31 shared benchmarks.
Mistral AISummary
- They share 31 benchmarks with published results for both. Mistral Medium scores higher in 2 categories and o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 84.4% for o3.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $8 for o3.
- Mistral Medium accepts more context: 262K tokens versus 200K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | o3 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 36.3 | 47.5 |
| Released | 2023-12-11 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $1.50 | $2 |
| Output $ / M tokens | $7.50 | $8 |
| Results tracked | 36 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Mistral Medium: 34.2 (#243), o3: 46.8 (#64)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| WeirdML | 43.7% | 52.4% |
| LMArena Coding | 1434 | 1408 |
| ALE-Bench | 763.98 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| FrontierCode | 8% | — |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 40.2% | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |
Agentic & Tool Use o3 leads
Mistral Medium: 28.3 (#90), o3: 34.5 (#44)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Mistral Medium: 24.0 (#167), o3: 32.0 (#78)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| Kagi LLM Benchmark | 50% | 67.6% |
| CritPt | 0% | 1.4% |
| LMArena Hard Prompts | 1426 | 1402 |
| DTBench | 75.5% | 84.8% |
| LMCA | 26.1% | 39.7% |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
Mistral Medium: 28.1 (#245), o3: 50.2 (#58)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 84.4% |
| LMArena Math | 1408 | 1426 |
| MATH Level 5 | 81.6% | 97.8% |
| FrontierMath (Feb 2025 set) | 0.3% | 18.7% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| ProofBench | 9% | — |
| Omni-MATH | — | 71.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Mistral Medium: 25.0 (#265), o3: 54.6 (#52)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| GPQA Diamond | 59.5% | 81.8% |
| Humanity's Last Exam | 4.5% | 20.3% |
| LMArena Expert | 1408 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 22.7% | — |
| GPQA (HELM) | — | 75.3% |
Multimodal o3 leads
Mistral Medium: 35.3 (#88), o3: 41.4 (#36)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| LMArena Vision | 1172 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Too close to call
Mistral Medium: 52.1 (#91), o3: 51.7 (#105)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| LMArena Non-English | 1408 | 1401 |
| LMArena Chinese | 1447 | 1437 |
| LMArena French | 1459 | 1430 |
| LMArena German | 1432 | 1420 |
| LMArena Japanese | 1378 | 1403 |
| LMArena Korean | 1380 | 1370 |
| LMArena Russian | 1411 | 1406 |
| LMArena Spanish | 1433 | 1395 |
Instruction Following Too close to call
Mistral Medium: 73.7 (#116), o3: 72.8 (#127)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Mistral Medium: 42.9 (#114), o3: 53.3 (#6)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Mistral Medium: 60.0 (#103), o3: 63.5 (#64)
| Benchmark | Mistral Medium | o3 |
|---|---|---|
| LMArena Text | 1424 | 1410 |
| LMArena Creative Writing | 1391 | 1359 |
| Short-Story Creative Writing | 77.3% | 83.9% |
| LMArena Multi-Turn | 1418 | 1405 |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Mistral Medium better than o3?
o3 is the stronger model overall, scoring 47.5 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or o3?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; o3 lists at $2 and $8.
Is Mistral Medium or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 200K.
How many benchmarks do Mistral Medium and o3 share?
31 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and o3 has 63.