Benchmark Almanac

KAT Claw Bench

KAT-Coder-Pro V2.5 85.5%
In use

Agents complete business tool-use tasks from Kuaishou internal agent needs in seven categories, such as office work, content operations, data analysis and monitoring. Automatic checks grade objective outputs, and model and human review grade open deliverables.

In-house Claw-style benchmark described in the KAT-Coder-V2.5 tech report.

Released
July 2026
Kind
General assistants
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Last in a launch post
July 2026
Last model added
July 2026
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

KAT-Coder-Pro V2.5 leads with 85.5%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 85.5 KAT-Coder-Pro V2.5
  1. 1 KAT-Coder-Pro V2.5 85.5%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 KAT-Coder-Pro V2.5 85.5% Jul 2026 Lab model card

Kuaishou’s own number for KAT-Coder-Pro V2.5 passed 85% in July 2026

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card
0% 20% 40% 60% 80% 100% Near the ceiling (85%) KAT-Coder-Pro V2.5 0% 20% 40% 60% 80% 100% Near the ceiling (85%) KAT-Coder-Pro V2.5

Source: Labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Kuaishou
DateLaunch postScoreAs the post writes it
Jul 6, 2026 KAT-Coder-Pro V2.5 85.5 KAT Claw Bench

More in Tool use

All 144 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Carbon 53.9%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%