Claw-Eval Benchmark Leaderboard | Phaseo

Claw-Eval

AI benchmark results and model performance

Type: percentageAgents

Recorded Results

13

Average Score

58.90%

Score Range

23.80% - 75%

Leading Model (lowest score)

23.80% - MiMo V2.5

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Xiaomi	MiMo V2 Omni	18 Mar 2026	54.80%	-	Yes	Source
DeepSeek	DeepSeek V4 Flash	24 Apr 2026	57.90%	Multi Turn; Hugging Face evaluation result	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	58.70%	-	Yes	Source
Xiaomi	MiMo V2 Pro	18 Mar 2026	61.50%	-	Yes	Source
Xiaomi	MiMo V2 TTS	18 Mar 2026	61.50%	inferred modality/version alias from mimo-v2-pro	Yes	Source
Xiaomi	MiMo V2.5	22 Apr 2026	63.20%	Multi Turn; Hugging Face evaluation result	Yes	Source
Qwen	Qwen 3.7 Max	21 May 2026	65.20%	-	Yes	Source
DeepSeek	DeepSeek V4 Pro	24 Apr 2026	65.80%	Multi Turn; Hugging Face evaluation result	Yes	Source
z.AI	GLM 5V Turbo	01 Apr 2026	75%	-	Yes	Source