Model comparison
Mistral Small 3.1 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 31.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
StepFunSummary
- They share 16 benchmarks with published results for both. Mistral Small 3.1 scores higher in 0 categories and Step 3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 14.7.
Side by side
| Mistral Small 3.1 | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 31.7 | 40.5 |
| Released | 2025-03-17 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 102K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $0.56 | — |
| Results tracked | 28 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Mistral Small 3.1: 38.3 (#179), Step 3: 40.1 (#147)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1309 | 1367 |
Reasoning Step 3 leads
Mistral Small 3.1: 19.7 (#254), Step 3: 28.4 (#105)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 127.48 | — |
Math Step 3 leads
Mistral Small 3.1: 14.7 (#301), Step 3: 37.6 (#148)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Math | 1262 | 1366 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |
Knowledge Step 3 leads
Mistral Small 3.1: 22.6 (#271), Step 3: 36.8 (#164)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1257 | 1333 |
| GPQA Diamond | 41.9% | — |
| MMLU-Pro | 61% | — |
| GPQA (HELM) | 39.2% | — |
Multimodal Step 3 leads
Mistral Small 3.1: 33.2 (#99), Step 3: 35.5 (#86)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Vision | 1136 | 1177 |
Multilingual Step 3 leads
Mistral Small 3.1: 41.2 (#209), Step 3: 46.3 (#159)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1255 | 1327 |
| LMArena Chinese | 1253 | 1397 |
| LMArena German | 1266 | 1371 |
| LMArena Korean | 1206 | 1269 |
| LMArena Russian | 1263 | 1331 |
| LMArena Spanish | 1283 | 1371 |
| LMArena French | 1273 | — |
| LMArena Japanese | 1208 | — |
Instruction Following Step 3 leads
Mistral Small 3.1: 63.6 (#230), Step 3: 70.4 (#164)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1264 | 1332 |
| IFEval | 75% | — |
Long Context Too close to call
Mistral Small 3.1: 39.5 (#178), Step 3: 40.3 (#157)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1299 | 1326 |
Writing & Preference Step 3 leads
Mistral Small 3.1: 37.0 (#259), Step 3: 54.3 (#151)
| Benchmark | Mistral Small 3.1 | Step 3 |
|---|---|---|
| LMArena Text | 1277 | 1350 |
| LMArena Creative Writing | 1253 | 1321 |
| LMArena Multi-Turn | 1270 | 1341 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
Frequently asked questions
Is Mistral Small 3.1 better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 31.7 on the Noometry Index.
Is Mistral Small 3.1 or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 38.3 in the Noometry coding category.
How many benchmarks do Mistral Small 3.1 and Step 3 share?
16 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Step 3 has 17.