Model comparison
Mistral Medium vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 36.3 on the Noometry Index.
Last verified . 32 shared benchmarks.
Mistral AISummary
- They share 32 benchmarks with published results for both. Mistral Medium scores higher in 2 categories and o4-mini in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.6 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 81.7% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- 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 | o4-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 36.3 | 41.6 |
| Released | 2023-12-11 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $1.50 | $1.10 |
| Output $ / M tokens | $7.50 | $4.40 |
| Results tracked | 36 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mistral Medium: 34.2 (#243), o4-mini: 40.9 (#127)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| WeirdML | 43.7% | 52.6% |
| LMArena Coding | 1434 | 1368 |
| ALE-Bench | 763.98 | 826.17 |
| FrontierCode | 8% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| SciCode | 40.2% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Mistral Medium: 28.3 (#90), o4-mini: 32.6 (#61)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning Too close to call
Mistral Medium: 24.0 (#167), o4-mini: 24.6 (#162)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 50% | 67.6% |
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1426 | 1351 |
| DTBench | 75.5% | 77.6% |
| LMCA | 26.1% | 26.5% |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| ARC-AGI-1 | — | 58.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
Mistral Medium: 28.1 (#245), o4-mini: 40.8 (#89)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 81.7% |
| LMArena Math | 1408 | 1389 |
| MATH Level 5 | 81.6% | 97.8% |
| FrontierMath (Feb 2025 set) | 0.3% | 24.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | 9% | — |
| Omni-MATH | — | 72% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mistral Medium: 25.0 (#265), o4-mini: 43.6 (#91)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| GPQA Diamond | 59.5% | 79.6% |
| Humanity's Last Exam | 4.5% | 18.1% |
| Vectara Hallucination Rate | 22.7% | 18.6% |
| LMArena Expert | 1408 | 1343 |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal o4-mini leads
Mistral Medium: 35.3 (#88), o4-mini: 40.2 (#49)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| LMArena Vision | 1172 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), o4-mini: 47.0 (#154)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| LMArena Non-English | 1408 | 1337 |
| LMArena Chinese | 1447 | 1354 |
| LMArena French | 1459 | 1364 |
| LMArena German | 1432 | 1336 |
| LMArena Japanese | 1378 | 1308 |
| LMArena Korean | 1380 | 1312 |
| LMArena Russian | 1411 | 1334 |
| LMArena Spanish | 1433 | 1347 |
Instruction Following o4-mini leads
Mistral Medium: 73.7 (#116), o4-mini: 75.2 (#68)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1398 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Mistral Medium: 42.9 (#114), o4-mini: 45.5 (#33)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| LMArena Longer Query | 1406 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), o4-mini: 54.0 (#152)
| Benchmark | Mistral Medium | o4-mini |
|---|---|---|
| LMArena Text | 1424 | 1353 |
| LMArena Creative Writing | 1391 | 1294 |
| Short-Story Creative Writing | 77.3% | 75% |
| LMArena Multi-Turn | 1418 | 1350 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Mistral Medium better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 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 o4-mini share?
32 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and o4-mini has 60.