Model comparison
Mistral 7B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 23.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Mistral AI
StepFunSummary
- They share 14 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 8.1.
Side by side
| Mistral 7B | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 23.0 | 40.5 |
| Released | 2023-09-27 | — |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Mistral 7B: 26.4 (#326), Step 3: 40.1 (#147)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Coding | 1082 | 1367 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Step 3 leads
Mistral 7B: 13.1 (#336), Step 3: 28.4 (#105)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Step 3 leads
Mistral 7B: 8.1 (#325), Step 3: 37.6 (#148)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Math | 1085 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Step 3 leads
Mistral 7B: 7.4 (#311), Step 3: 36.8 (#164)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Expert | 1036 | 1333 |
| GPQA Diamond | 15.2% | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multimodal Not comparable
Mistral 7B: —, Step 3: 35.5 (#86)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Mistral 7B: 25.8 (#283), Step 3: 46.3 (#159)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Non-English | 1012 | 1327 |
| LMArena Chinese | 1009 | 1397 |
| LMArena German | 987 | 1371 |
| LMArena Russian | 1018 | 1331 |
| LMArena Spanish | 1026 | 1371 |
| LMArena French | 1037 | — |
| LMArena Japanese | 878 | — |
| LMArena Korean | — | 1269 |
Instruction Following Step 3 leads
Mistral 7B: 54.2 (#280), Step 3: 70.4 (#164)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1060 | 1332 |
Long Context Step 3 leads
Mistral 7B: 32.2 (#271), Step 3: 40.3 (#157)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1060 | 1326 |
Writing & Preference Step 3 leads
Mistral 7B: 30.7 (#286), Step 3: 54.3 (#151)
| Benchmark | Mistral 7B | Step 3 |
|---|---|---|
| LMArena Text | 1090 | 1350 |
| LMArena Creative Writing | 1068 | 1321 |
| LMArena Multi-Turn | 1062 | 1341 |
Frequently asked questions
Is Mistral 7B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 23.0 on the Noometry Index.
Is Mistral 7B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Step 3 share?
14 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Step 3 has 17.