Model comparison
Mistral Small 3 vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 30.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Mistral AI
StepFunSummary
- They share 14 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.5 to 32.4.
Side by side
| Mistral Small 3 | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 30.9 | 39.9 |
| Released | 2025-01-30 | — |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Mistral Small 3: 36.0 (#203), Step 3: 39.5 (#144)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Coding | 1246 | 1367 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Step 3 leads
Mistral Small 3: 18.2 (#269), Step 3: 27.6 (#102)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.06 | — |
Math Step 3 leads
Mistral Small 3: 15.3 (#290), Step 3: 34.9 (#148)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Math | 1240 | 1366 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Step 3 leads
Mistral Small 3: 25.0 (#258), Step 3: 36.2 (#161)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Expert | 1202 | 1333 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Step 3: 34.9 (#81)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Step 3 leads
Mistral Small 3: 37.5 (#231), Step 3: 46.5 (#154)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Non-English | 1198 | 1327 |
| LMArena Chinese | 1204 | 1396 |
| LMArena German | 1211 | 1371 |
| LMArena Korean | 1188 | 1271 |
| LMArena Russian | 1216 | 1331 |
| LMArena French | 1202 | — |
| LMArena Japanese | 1111 | — |
| LMArena Spanish | — | 1372 |
Instruction Following Step 3 leads
Mistral Small 3: 63.9 (#224), Step 3: 70.6 (#159)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1214 | 1332 |
Long Context Step 3 leads
Mistral Small 3: 37.8 (#206), Step 3: 40.3 (#152)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1246 | 1326 |
Writing & Preference Step 3 leads
Mistral Small 3: 32.4 (#275), Step 3: 54.5 (#146)
| Benchmark | Mistral Small 3 | Step 3 |
|---|---|---|
| LMArena Text | 1234 | 1351 |
| LMArena Creative Writing | 1195 | 1322 |
| LMArena Multi-Turn | 1217 | 1340 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 30.9 on the Noometry Index.
Is Mistral Small 3 or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 36.0 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Step 3 share?
14 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Step 3 has 17.