Model comparison
Mistral Large vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 31.6 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
StepFunSummary
- They share 2 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 15.4.
- The biggest single-benchmark swing is SciCode: 36.2% for Mistral Large and 58.9% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $6 for Mistral Large.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 31.6 | 43.8 |
| Released | 2024-02-26 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.02M |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $6 | $2.70 |
| Results tracked | 51 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Mistral Large: 33.8 (#240), Step 5 Preview: 50.6 (#40)
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| SciCode | 36.2% | 58.9% |
| LMArena WebDev | — | 1569 |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| LMArena Coding | 1277 | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.4 (#83), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Step 5 Preview leads
Mistral Large: 15.4 (#305), Step 5 Preview: 38.0 (#58)
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| SimpleBench | 22.5% | — |
| LiveBench Reasoning | 43.5% | — |
| LMArena Hard Prompts | 1257 | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Not comparable
Mistral Large: 17.1 (#285), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| LMArena Math | 1262 | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Mistral Large: 30.0 (#224), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| LMArena Expert | 1232 | — |
| MMLU | 80% | — |
Multilingual Not comparable
Mistral Large: 40.1 (#214), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1237 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1324 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1187 | — |
| LMArena Korean | 1202 | — |
| LMArena Russian | 1257 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Not comparable
Mistral Large: 68.1 (#186), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
| LMArena Instruction Following | 1249 | — |
Long Context Not comparable
Mistral Large: 38.3 (#194), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1262 | — |
Writing & Preference Not comparable
Mistral Large: 40.9 (#237), Step 5 Preview: —
| Benchmark | Mistral Large | Step 5 Preview |
|---|---|---|
| LMArena Text | 1266 | — |
| LMArena Creative Writing | 1243 | — |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LMArena Multi-Turn | 1260 | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 31.6 on the Noometry Index.
Which is cheaper, Mistral Large or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 131K.
How many benchmarks do Mistral Large and Step 5 Preview share?
2 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Step 5 Preview has 3.