Model comparison
Mistral Medium 3.5 vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 39.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 2 categories and o4-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o4-mini leads 24.6 to 16.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 41.4% for Mistral Medium 3.5 and 67.6% 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 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 200K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium 3.5 | o4-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 39.6 | 41.6 |
| Released | — | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 210K | 100K |
| Input $ / M tokens | $1.50 | $1.10 |
| Output $ / M tokens | $7.50 | $4.40 |
| Results tracked | 22 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mistral Medium 3.5: 35.7 (#208), o4-mini: 41.6 (#110)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Coding | 1461 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1263 | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Mistral Medium 3.5: —, o4-mini: 32.3 (#57)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Mistral Medium 3.5: 16.6 (#290), o4-mini: 24.6 (#143)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 41.4% | 67.6% |
| LMArena Hard Prompts | 1436 | 1351 |
| Epoch Capabilities Index | 141.42 | 145.63 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| NYT Connections (extended) | 12.9% | — |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| ForecastBench | — | 61.8 |
Math o4-mini leads
Mistral Medium 3.5: 36.4 (#113), o4-mini: 40.2 (#79)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Math | 1432 | 1390 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mistral Medium 3.5: 39.3 (#123), o4-mini: 43.5 (#83)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Expert | 1431 | 1344 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal o4-mini leads
Mistral Medium 3.5: 37.6 (#64), o4-mini: 39.5 (#46)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Vision | 1222 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Mistral Medium 3.5 leads
Mistral Medium 3.5: 52.1 (#93), o4-mini: 47.2 (#149)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Non-English | 1405 | 1336 |
| LMArena Chinese | 1443 | 1355 |
| LMArena French | 1448 | 1362 |
| LMArena German | 1453 | 1336 |
| LMArena Korean | 1387 | 1313 |
| LMArena Russian | 1396 | 1334 |
| LMArena Spanish | 1406 | 1346 |
| LMArena Japanese | — | 1308 |
Instruction Following Too close to call
Mistral Medium 3.5: 74.7 (#87), o4-mini: 75.4 (#63)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1414 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Mistral Medium 3.5: 43.2 (#101), o4-mini: 45.5 (#31)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1414 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Mistral Medium 3.5 leads
Mistral Medium 3.5: 58.6 (#113), o4-mini: 54.2 (#148)
| Benchmark | Mistral Medium 3.5 | o4-mini |
|---|---|---|
| LMArena Text | 1421 | 1353 |
| LMArena Creative Writing | 1372 | 1294 |
| LMArena Multi-Turn | 1423 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 39.6 on the Noometry Index.
Which is cheaper, Mistral Medium 3.5 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 3.5 lists at $1.50 and $7.50.
Is Mistral Medium 3.5 or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 41.6 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 200K.
How many benchmarks do Mistral Medium 3.5 and o4-mini share?
19 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and o4-mini has 60.