Model comparison
Ministral 3B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 26.2 on the Noometry Index. Ministral 3B costs 1.5× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
StepFunSummary
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.6 to 10.4.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Ministral 3B | Step 3.5 Flash | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 26.2 | 42.3 |
| Released | 2024-10-01 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 262K | 256K |
| Input $ / M tokens | $0.10 | $0.10 |
| Output $ / M tokens | $0.10 | $0.30 |
| Results tracked | 6 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Step 3.5 Flash: 42.4 (#105)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | — | 1436 |
Reasoning Step 3.5 Flash leads
Ministral 3B: 18.4 (#282), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | — | 28.4% |
| LMArena Hard Prompts | — | 1411 |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 118.1 | — |
Math Step 3.5 Flash leads
Ministral 3B: 26.6 (#258), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |
| MATH Level 5 | 14.4% | — |
Knowledge Step 3.5 Flash leads
Ministral 3B: 10.4 (#302), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| GPQA Diamond | 25.3% | — |
| Vectara Hallucination Rate | 7.3% | — |
| LMArena Expert | — | 1421 |
Multilingual Not comparable
Ministral 3B: —, Step 3.5 Flash: 50.5 (#119)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Ministral 3B: —, Step 3.5 Flash: 73.1 (#124)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Not comparable
Ministral 3B: —, Step 3.5 Flash: 42.8 (#117)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Ministral 3B: —, Step 3.5 Flash: 58.8 (#113)
| Benchmark | Ministral 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Ministral 3B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 26.2 on the Noometry Index. Ministral 3B costs 1.5× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or Step 3.5 Flash?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 131K.
How many benchmarks do Ministral 3B and Step 3.5 Flash share?
0 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Step 3.5 Flash has 19.