Model comparison
Mistral Small 3 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.2 on the Noometry Index. Mistral Small 3 costs 25× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AI
StepFunSummary
- They share 12 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 31.2 | 47.9 |
| Released | 2025-01-30 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 33K | 1.02M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.05 | $1 |
| Output $ / M tokens | $0.08 | $2.70 |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Mistral Small 3: 36.5 (#207), Step 5 Preview: 51.8 (#36)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1246 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Step 5 Preview leads
Mistral Small 3: 18.9 (#273), Step 5 Preview: 40.0 (#57)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.07 | — |
Math Step 5 Preview leads
Mistral Small 3: 16.3 (#295), Step 5 Preview: 46.1 (#72)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1240 | 1470 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| ProofBench | — | 42% |
Knowledge Step 5 Preview leads
Mistral Small 3: 25.1 (#263), Step 5 Preview: 41.2 (#112)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1202 | 1470 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Mistral Small 3: 37.3 (#236), Step 5 Preview: 53.8 (#54)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1198 | 1432 |
| LMArena Chinese | 1204 | 1519 |
| LMArena Russian | 1216 | 1436 |
| LMArena French | 1203 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Mistral Small 3: 63.7 (#229), Step 5 Preview: 76.0 (#50)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1214 | 1444 |
Long Context Step 5 Preview leads
Mistral Small 3: 37.8 (#211), Step 5 Preview: 44.5 (#64)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1246 | 1455 |
Writing & Preference Step 5 Preview leads
Mistral Small 3: 32.2 (#280), Step 5 Preview: 62.8 (#71)
| Benchmark | Mistral Small 3 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1234 | 1442 |
| LMArena Creative Writing | 1195 | 1410 |
| LMArena Multi-Turn | 1217 | 1447 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.2 on the Noometry Index. Mistral Small 3 costs 25× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Step 5 Preview?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Mistral Small 3 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 33K.
How many benchmarks do Mistral Small 3 and Step 5 Preview share?
12 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Step 5 Preview has 18.