KAT-Coder-Pro V2.5.

specs at a glance

how good is KAT-Coder-Pro V2.5 at coding?

KAT-Coder-Pro V2.5 is on our board but deliberately unranked. We rank by SWE-bench Verified, Kwaipilot (Kuaishou) 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 65.2% on SWE-bench Pro, 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. On the harder SWE-bench Pro it scores 65.2%.

Score provenance: Vendor-reported (KAT-Coder-V2.5 technical report, arXiv 2607.05471): SWE-bench Pro 65.2%, second only to Opus 4.8 at 69.2%, plus a best-in-test PinchBench 94.9% for agentic tool use, all run under a unified Claude Code harness. No SWE-bench Verified score published for V2.5, so it stays unranked pending independent confirmation. vals.ai has not evaluated it and does not cover Kwaipilot/Kuaishou at all, and llm-stats does not list the model.

Pricing confirmed at $0.74/$2.96 per 1M (Pro) and $0.15/$0.60 (Air). Re-checked 2026-09-09: vals.ai's SWE-bench Verified board is unchanged since the September 1 archival and still shows no evaluation for this model; all previously-tracked ranked scores were also re-verified this run and hold within normal variance (largest drift under 0.4pp).

what does KAT-Coder-Pro V2.5 cost?

$0.74 per 1M input tokens and $2.96 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, via the StreamLake platform; integrates with Claude Code and OpenHands. As a proprietary model, you're on the maker's infrastructure and release schedule.

Full storyKAT-Coder-Pro V2.5 Lands Second on SWE-Bench Pro

Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-09-03.