Model comparison
Mistral 7B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 23.0 on the Noometry Index. Mistral 7B costs 5.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AI
StepFunSummary
- They share 13 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 8.1.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| Mistral 7B | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 23.0 | 47.9 |
| Released | 2023-09-27 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 8K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $1 |
| Output $ / M tokens | $0.25 | $2.70 |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Mistral 7B: 26.4 (#326), Step 5 Preview: 51.8 (#36)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1082 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Step 5 Preview leads
Mistral 7B: 13.1 (#336), Step 5 Preview: 40.0 (#57)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1465 |
| CritPt | — | 20.9% |
| 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 5 Preview leads
Mistral 7B: 8.1 (#325), Step 5 Preview: 46.1 (#72)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1085 | 1470 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| ProofBench | — | 42% |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Step 5 Preview leads
Mistral 7B: 7.4 (#311), Step 5 Preview: 41.2 (#112)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1036 | 1470 |
| 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 5 Preview: 41.0 (#41)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Mistral 7B: 25.8 (#283), Step 5 Preview: 53.8 (#54)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1012 | 1432 |
| LMArena Chinese | 1009 | 1519 |
| LMArena Russian | 1018 | 1436 |
| LMArena Spanish | 1026 | 1439 |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
Instruction Following Step 5 Preview leads
Mistral 7B: 54.2 (#280), Step 5 Preview: 76.0 (#50)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1060 | 1444 |
Long Context Step 5 Preview leads
Mistral 7B: 32.2 (#271), Step 5 Preview: 44.5 (#64)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1060 | 1455 |
Writing & Preference Step 5 Preview leads
Mistral 7B: 30.7 (#286), Step 5 Preview: 62.8 (#71)
| Benchmark | Mistral 7B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1090 | 1442 |
| LMArena Creative Writing | 1068 | 1410 |
| LMArena Multi-Turn | 1062 | 1447 |
Frequently asked questions
Is Mistral 7B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 23.0 on the Noometry Index. Mistral 7B costs 5.7× 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 7B or Step 5 Preview?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Mistral 7B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 8K.
How many benchmarks do Mistral 7B and Step 5 Preview share?
13 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Step 5 Preview has 18.