Model comparison
Mistral Medium vs Mistral Small 3.1
Mistral Medium is the stronger model overall, scoring 36.3 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 7.5× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Mistral Medium scores higher in 8 categories and Mistral Small 3.1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 37.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Mistral Medium | Mistral Small 3.1 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 36.3 | 31.7 |
| Released | 2023-12-11 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 262K | 102K |
| Input $ / M tokens | $1.50 | $0.35 |
| Output $ / M tokens | $7.50 | $0.56 |
| Results tracked | 36 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Medium: 34.2 (#243), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1434 | 1309 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Mistral Small 3.1: —
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1278 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 127.48 |
Math Mistral Medium leads
Mistral Medium: 28.1 (#245), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 3.9% |
| LMArena Math | 1408 | 1262 |
| ProofBench | 9% | — |
| Omni-MATH | — | 24.8% |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Medium leads
Mistral Medium: 25.0 (#265), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 59.5% | 41.9% |
| LMArena Expert | 1408 | 1257 |
| Humanity's Last Exam | 4.5% | — |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 22.7% | — |
| GPQA (HELM) | — | 39.2% |
Multimodal Mistral Medium leads
Mistral Medium: 35.3 (#88), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1172 | 1136 |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1408 | 1255 |
| LMArena Chinese | 1447 | 1253 |
| LMArena French | 1459 | 1273 |
| LMArena German | 1432 | 1266 |
| LMArena Japanese | 1378 | 1208 |
| LMArena Korean | 1380 | 1206 |
| LMArena Russian | 1411 | 1263 |
| LMArena Spanish | 1433 | 1283 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1264 |
| IFEval | — | 75% |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1406 | 1299 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Mistral Medium | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1424 | 1277 |
| LMArena Creative Writing | 1391 | 1253 |
| LMArena Multi-Turn | 1418 | 1270 |
| Short-Story Creative Writing | 77.3% | — |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
Frequently asked questions
Is Mistral Medium better than Mistral Small 3.1?
Mistral Medium is the stronger model overall, scoring 36.3 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 7.5× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Mistral Medium or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do Mistral Medium and Mistral Small 3.1 share?
20 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Mistral Small 3.1 has 28.