Model comparison
Ministral 8B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
StepFunSummary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 12.6.
Side by side
| Ministral 8B | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 28.2 | 40.5 |
| Released | 2024-10-01 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Ministral 8B: 35.0 (#230), Step 3: 40.1 (#147)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Coding | 1202 | 1367 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Step 3: —
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Step 3 leads
Ministral 8B: 18.4 (#281), Step 3: 28.4 (#105)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| DTBench | 45.7% | — |
Math Step 3 leads
Ministral 8B: 25.7 (#267), Step 3: 37.6 (#148)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Math | 1188 | 1366 |
| MATH Level 5 | 14.9% | — |
Knowledge Step 3 leads
Ministral 8B: 12.6 (#297), Step 3: 36.8 (#164)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Expert | 1170 | 1333 |
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Ministral 8B: —, Step 3: 35.5 (#86)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Ministral 8B: 35.1 (#247), Step 3: 46.3 (#159)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Non-English | 1165 | 1327 |
| LMArena Chinese | 1193 | 1397 |
| LMArena Russian | 1195 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Ministral 8B: 60.5 (#250), Step 3: 70.4 (#164)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1161 | 1332 |
Long Context Step 3 leads
Ministral 8B: 36.7 (#227), Step 3: 40.3 (#157)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1212 | 1326 |
Writing & Preference Step 3 leads
Ministral 8B: 39.6 (#246), Step 3: 54.3 (#151)
| Benchmark | Ministral 8B | Step 3 |
|---|---|---|
| LMArena Text | 1191 | 1350 |
| LMArena Creative Writing | 1175 | 1321 |
| LMArena Multi-Turn | 1166 | 1341 |
Frequently asked questions
Is Ministral 8B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 28.2 on the Noometry Index.
Is Ministral 8B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 35.0 in the Noometry coding category.
How many benchmarks do Ministral 8B and Step 3 share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Step 3 has 17.