Loading benchmark catalogue
Compare performance benchmarks, coding intelligence, reasoning evaluations, context limits, and API economics between Mistral Large 4 (Mistral AI) and Step 5 Preview (StepFun).
| Metric / Capability | Mistral Large 4 | Step 5 Preview |
|---|---|---|
| Developer / Organization | Mistral AI | StepFun |
| Release Date | 2026-10-06 | 2026-10-08 |
| Deployment / Weights | Proprietary Cloud API | Open Weights |
| Context Window | 1.0M tokens (1,048,576 tokens) | 1.0M tokens (1,048,576 tokens) |
| Input Pricing (/1M Tokens) | $1.36 | Free (Open Weights) |
| Output Pricing (/1M Tokens) | $4.18 | Free (Open Weights) |
| Benchmark / Domain | Mistral Large 4 | Step 5 Preview | Advantage |
|---|---|---|---|
Artificial Analysis Intelligence Index Composite index aggregating 10+ evaluations of general reasoning and knowledge. | 38.4% | 43.7% | Step 5 Preview (+14%) |
Artificial Analysis Coding Agent Index v2.0 Composite index of coding-agent systems (model + harness) across FrontierCode v1.1, SWE-Atlas-QnA, and Terminal-Bench v4. | — | 43.1% | — |
Terminal-Bench 4.0 Sandboxed command-line tasks requiring shell and file-system operation. | — | 33.3% | — |
GPQA Diamond Graduate-level physics, chemistry, and biology questions written by domain experts. | — | 93.5% | — |
Humanity's Last Exam Expert-written questions across hundreds of disciplines designed to resist saturation. | — | 46.5% | — |
Design Arena ELO Human-preference ELO across UI, 3D, data-visualization, and game-dev generations. | 1275 | — | — |
Step 5 Preview outperforms Mistral Large 4 across 1 evaluated benchmarks compared to 0 for Mistral Large 4, excelling in Artificial Analysis Intelligence Index.
Both models feature equivalent context windows of 1.0M tokens (1,048,576 tokens).
Step 5 Preview is more economical. Input tokens cost $Free (Open Weights)/M tokens compared to $1.36/M tokens for Mistral Large 4.
Mistral Large 4 is a proprietary cloud API. Step 5 Preview is an open-weights model.
Analyze 130+ models side-by-side using interactive radar charts, cost-efficiency quadrant plots, and live dataset filters on the full NeuBench index.
Open Interactive Comparator