Model comparison
Mistral Medium vs o1
o1 is the stronger model overall, scoring 40.9 to 36.3 on the Noometry Index. Mistral Medium costs 8.8× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and o1 in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1 leads 41.5 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 73.3% for o1.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $15 / $60 for o1.
- 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 | o1 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 36.3 | 40.9 |
| Released | 2023-12-11 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $1.50 | $15 |
| Output $ / M tokens | $7.50 | $60 |
| Results tracked | 36 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Mistral Medium: 34.2 (#243), o1: 46.1 (#70)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| WeirdML | 43.7% | 47.6% |
| LMArena Coding | 1434 | 1367 |
| FrontierCode | 8% | — |
| Aider Polyglot | — | 61.7% |
| SciCode | 40.2% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 763.98 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Mistral Medium leads
Mistral Medium: 28.3 (#90), o1: 24.6 (#117)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Mistral Medium: 24.0 (#167), o1: 27.9 (#111)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1371 |
| DTBench | 75.5% | 74.7% |
| LMCA | 26.1% | 22.3% |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 50% | — |
| ARC-AGI-1 | — | 30.7% |
| CritPt | 0% | — |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 141.91 |
| LiveBench | — | 75.7% |
Math o1 leads
Mistral Medium: 28.1 (#245), o1: 36.1 (#175)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 73.3% |
| LMArena Math | 1408 | 1388 |
| MATH Level 5 | 81.6% | 94.7% |
| FrontierMath (Feb 2025 set) | 0.3% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| ProofBench | 9% | — |
| LiveBench Math | — | 80.3% |
Knowledge o1 leads
Mistral Medium: 25.0 (#265), o1: 41.5 (#110)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| GPQA Diamond | 59.5% | 76.8% |
| Humanity's Last Exam | 4.5% | 8% |
| LMArena Expert | 1408 | 1361 |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Mistral Medium leads
Mistral Medium: 35.3 (#88), o1: 34.2 (#93)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Vision | 1172 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), o1: 48.6 (#142)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Non-English | 1408 | 1358 |
| LMArena Chinese | 1447 | 1394 |
| LMArena French | 1459 | 1344 |
| LMArena German | 1432 | 1337 |
| LMArena Japanese | 1378 | 1346 |
| LMArena Korean | 1380 | 1396 |
| LMArena Russian | 1411 | 1356 |
| LMArena Spanish | 1433 | 1345 |
Instruction Following o1 leads
Mistral Medium: 73.7 (#116), o1: 74.8 (#86)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Mistral Medium: 42.9 (#114), o1: 50.3 (#9)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Longer Query | 1406 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), o1: 55.6 (#144)
| Benchmark | Mistral Medium | o1 |
|---|---|---|
| LMArena Text | 1424 | 1366 |
| LMArena Creative Writing | 1391 | 1348 |
| Short-Story Creative Writing | 77.3% | 70.2% |
| LMArena Multi-Turn | 1418 | 1369 |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Mistral Medium better than o1?
o1 is the stronger model overall, scoring 40.9 to 36.3 on the Noometry Index. Mistral Medium costs 8.8× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Mistral Medium or o1?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; o1 lists at $15 and $60.
Is Mistral Medium or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 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 o1 share?
27 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and o1 has 52.