HumanEval-Mul Benchmark Leaderboard | Phaseo

HumanEval-Mul

AI benchmark results and model performance

Type: numericalReasoning

Recorded Results

5

Average Score

0.79

Score Range

0.74 - 0.83

Leading Model (lowest score)

0.74 - DeepSeek V2.5 (2024-09-05)

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
DeepSeek	DeepSeek V2.5 (2024-09-05)	05 Sept 2024	0.74	inferred alias from deepseek-v2.5	Yes	Source
DeepSeek	DeepSeek V2.5 (2024-12-10)	10 Dec 2024	0.74	inferred alias from deepseek-v2.5	Yes	Source
DeepSeek	DeepSeek OCR	20 Oct 2025	0.83	inferred family alias from deepseek-v3 (score=0.3000; benches=20)	Yes	Source
DeepSeek	DeepSeek V2 (2024-06-28)	28 Jun 2024	0.83	inferred family alias from deepseek-v3 (score=0.4159; benches=20)	Yes	Source
DeepSeek	DeepSeek V4	-	0.83	inferred high-confidence family alias from deepseek-v3 (score=0.5818; benches=20)	Yes	Source