Model comparison
Mistral Small vs Mistral Small 3.1
Mistral Small is the stronger model overall, scoring 33.4 to 31.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Mistral Small scores higher in 8 categories and Mistral Small 3.1 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 37.0.
- The biggest single-benchmark swing is GPQA Diamond: 47.5% for Mistral Small and 41.9% for Mistral Small 3.1.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
- Mistral Small accepts more context: 262K tokens versus 128K.
Side by side
| Mistral Small | Mistral Small 3.1 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 33.4 | 31.7 |
| Released | 2024-02-26 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 256K | 102K |
| Input $ / M tokens | $0.15 | $0.35 |
| Output $ / M tokens | $0.60 | $0.56 |
| Results tracked | 39 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Small: 34.0 (#247), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1362 | 1309 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Mistral Small 3.1: —
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Too close to call
Mistral Small: 19.8 (#250), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1278 |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 127.48 |
| LiveBench | 44% | — |
Math Mistral Small leads
Mistral Small: 16.4 (#293), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 3.9% |
| LMArena Math | 1341 | 1262 |
| Omni-MATH | — | 24.8% |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Mistral Small leads
Mistral Small: 31.0 (#222), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 47.5% | 41.9% |
| LMArena Expert | 1291 | 1257 |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | — | 39.2% |
| MMLU | 68.7% | — |
Multimodal Too close to call
Mistral Small: 33.5 (#96), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1142 | 1136 |
Multilingual Mistral Small leads
Mistral Small: 45.5 (#169), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1315 | 1255 |
| LMArena Chinese | 1340 | 1253 |
| LMArena French | 1337 | 1273 |
| LMArena German | 1340 | 1266 |
| LMArena Japanese | 1275 | 1208 |
| LMArena Korean | 1259 | 1206 |
| LMArena Russian | 1324 | 1263 |
| LMArena Spanish | 1346 | 1283 |
Instruction Following Mistral Small leads
Mistral Small: 66.4 (#209), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1310 | 1264 |
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 75% |
Long Context Too close to call
Mistral Small: 40.4 (#156), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1327 | 1299 |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Mistral Small | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1338 | 1277 |
| LMArena Creative Writing | 1305 | 1253 |
| LMArena Multi-Turn | 1344 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Mistral Small 3.1?
Mistral Small is the stronger model overall, scoring 33.4 to 31.7 on the Noometry Index.
Which is cheaper, Mistral Small or Mistral Small 3.1?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is Mistral Small or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 128K.
How many benchmarks do Mistral Small and Mistral Small 3.1 share?
20 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Mistral Small 3.1 has 28.