Kimi Claw 24/7 Bench

GPT-5.5 52.8% leads since June 2026

In use

Labs’ own numbers All independent runs

Agents work on 17 persistent multi-day professional scenarios through OpenClaw, with 610 checkpoints. The score is the mean pass rate over three runs.

In-house: Moonshot never released the tasks.

Made by: Moonshot AI
Released: June 2026
Kind: Tasks from real jobs
Level: Expert
Scored: Checked automatically
Answers: Agent task
Tasks: Kept private

Strongest model tested: GPT-5.5 #20 on the capability index
Last in a launch post: June 2026
Last model added: June 2026
Scores refreshed: November 12th, 2026

Model scored in lab cards

Launch post lists it, from 1 lab

Kimi K2.7 Code leads with 46.9%

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.

GPT-5.5 leads with 52.8% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

Bars Table

46.9 Kimi K2.7 Code

1 Kimi K2.7 Code 46.9%

Source: Labs’ model cards

Source: Official Kimi Claw 24/7 Bench leaderboard

#	Model	Score	Setting	Date	Source
1	Kimi K2.7 Code	46.9%		Jun 2026	Lab model card

#	Model	Score	Setting	Date	Source
1	GPT-5.5	52.8%	average pass rate over 610 evaluation points; mean of 3 runs, OpenClaw	Apr 2026	Official leaderboard
2	Claude Opus 4.8	50.4%	average pass rate over 610 evaluation points; mean of 3 runs, OpenClaw	May 2026	Official leaderboard
3	Kimi K2.7 Code	46.9%	average pass rate over 610 evaluation points; mean of 3 runs, OpenClaw	Jun 2026	Official leaderboard
4	Kimi K2.6	42.9%	average pass rate over 610 evaluation points; mean of 3 runs, OpenClaw	Apr 2026	Official leaderboard

The benchmark's own leaderboard has 4 models. Switch the scores above to rank them together.

Number one over time Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI

Own leaderboard Not tested since Jun 2026

GPT-5.5 52.8%

Source: Official Kimi Claw 24/7 Bench leaderboard

Scores over time

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

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official Kimi Claw 24/7 Bench leaderboard and 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.

Moonshot AI

Date	Launch post	Score	As the post writes it
Jun 12, 2026	Kimi K2.7 Code	46.9	Kimi Claw 24/7 Bench

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
Kimi K2.7 Code	46.9% Kimi Claw 24/7 Bench	46.9% Leaderboard, average pass rate over 610 evaluation points; mean of 3 runs, OpenClaw	Same