StepFun: Step 3.7 Flash wins on more metrics (5 of 6), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Mistral: Mistral Medium 3.5 | StepFun: Step 3.7 Flash |
|---|---|---|
| Intelligence Index | 29.9 | 30.3✓ |
| Coding Index | 46.9✓ | 39.6 |
| GPQA Diamond | 75% | 81%✓ |
| Design Arena Elo | 1166 | 1212✓ |
| Speed (tokens/sec) | — | — |
| Latency | — | — |
| Input price /M | $1.50 | $0.200✓ |
| Output price /M | $7.50 | $1.15✓ |
| Context window | 262K | 262K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |
StepFun: Step 3.7 Flash wins on more metrics (5 of 6), but the right pick depends on what you optimize for — see the breakdown below.
The table on this page compares Mistral: Mistral Medium 3.5 and StepFun: Step 3.7 Flash metric by metric — intelligence benchmarks, coding score, speed, latency, context window and per-token price — with the winner marked on each row. Data refreshes hourly.