Model comparison
Mistral Small vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 33.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
StepFunSummary
- They share 17 benchmarks with published results for both. Mistral Small scores higher in 1 category and Step 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 16.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Mistral Small and 62.3% for Step 3.
Side by side
| Mistral Small | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 33.4 | 40.5 |
| Released | 2024-02-26 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 39 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Mistral Small: 34.0 (#247), Step 3: 40.1 (#147)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Coding | 1362 | 1367 |
| 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), Step 3: —
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Step 3 leads
Mistral Small: 19.8 (#250), Step 3: 28.4 (#105)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 62.3% |
| LMArena Hard Prompts | 1335 | 1355 |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |
Math Step 3 leads
Mistral Small: 16.4 (#293), Step 3: 37.6 (#148)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Math | 1341 | 1366 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Step 3 leads
Mistral Small: 31.0 (#222), Step 3: 36.8 (#164)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Expert | 1291 | 1333 |
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Step 3 leads
Mistral Small: 33.5 (#96), Step 3: 35.5 (#86)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Vision | 1142 | 1177 |
Multilingual Too close to call
Mistral Small: 45.5 (#169), Step 3: 46.3 (#159)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Non-English | 1315 | 1327 |
| LMArena Chinese | 1340 | 1397 |
| LMArena German | 1340 | 1371 |
| LMArena Korean | 1259 | 1269 |
| LMArena Russian | 1324 | 1331 |
| LMArena Spanish | 1346 | 1371 |
| LMArena French | 1337 | — |
| LMArena Japanese | 1275 | — |
Instruction Following Step 3 leads
Mistral Small: 66.4 (#209), Step 3: 70.4 (#164)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1310 | 1332 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Too close to call
Mistral Small: 40.4 (#156), Step 3: 40.3 (#157)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Longer Query | 1327 | 1326 |
Writing & Preference Step 3 leads
Mistral Small: 52.5 (#171), Step 3: 54.3 (#151)
| Benchmark | Mistral Small | Step 3 |
|---|---|---|
| LMArena Text | 1338 | 1350 |
| LMArena Creative Writing | 1305 | 1321 |
| LMArena Multi-Turn | 1344 | 1341 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 33.4 on the Noometry Index.
Is Mistral Small or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 34.0 in the Noometry coding category.
How many benchmarks do Mistral Small and Step 3 share?
17 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Step 3 has 17.