specs at a glance
| Leaderboard status | Verifying — no confirmed SWE-bench Verified score |
|---|---|
| SWE-bench Verified | — |
| SWE-bench Pro | — |
| Terminal-Bench | 33.3 (TB4, vendor) |
| Input price / 1M | $1.00 |
| Output price / 1M | $2.70 |
| Context window | 1M |
| Open weights | No |
| Access | API only (platform.stepfun.ai); StepFun says open weights follow on Oct 15, 2026, license unstated |
| Maker | StepFun |
how good is Step 5 Preview at coding?
Step 5 Preview is on our board but deliberately unranked. We rank by SWE-bench Verified, StepFun has not published that number, and no independent evaluation has run it, so there is nothing here we could stand behind. What the maker does publish is 33.3 (TB4, vendor) on Terminal-Bench, measured on its own scaffold and not comparable like-for-like with the ranked rows. It moves into the ranking the moment a confirmed score exists. Terminal-Bench (agentic terminal work): 33.3 (TB4, vendor).
Score provenance: Vendor-reported (StepFun, Sept 20 2026): Terminal-Bench v4 33.3% (vs Claude Opus 5 52.3%, GPT-6 Astra 57.9%), DeepSWE v1.1 67.7%, ProgramBench 80.5%, StepCodeBench 49, Agents' Last Exam 29.5%, FrontierFinance 66.4%, DRACO 83.3%. StepFun published NO SWE-bench Verified score and no SWE-bench Pro, so there is nothing to rank on our tracked metric; it enters the verifying queue unranked.
Independent context, not a SWE-bench number: Artificial Analysis scores it 44 on its Intelligence Index (27th of 653), tied with Kimi K3 (max) at roughly 65% lower cost per task, at about 99.8 output tokens/s. Price confirmed via Artificial Analysis: $1.00/$2.70 per 1M, cached input about $0.05. Re-checked 2026-09-21: vals.ai's SWE-bench Verified board remains archived since September 1 (frozen for posterity, no new models are being scored) and shows no evaluation for this model.
See /p/stepfun-step-5-preview-600b-moe-1-dollar-per-million-tokens/.
what does Step 5 Preview cost?
$1.00 per 1M input tokens and $2.70 per 1M output — as listed by the maker. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.
where can you use it?
Available via API only (platform.stepfun.ai); StepFun says open weights follow on Oct 15, 2026, license unstated. As a proprietary model, you're on the maker's infrastructure and release schedule.
Full storyStepFun Step 5 Preview: a 600B Agent Model at $1 per Million Tokens
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-09-03.