HumanEval

Explore score history ↗

HumanEval is an AI benchmark in the Benchmark Radar catalog.

Released: 2021-07-08
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

HumanEval results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude 3.5 Sonnet	—	93.7	—	evidence
GPT-5	—	93.4	—	evidence
Kimi K2 0905	—	94.5	—	evidence
Kimi K2 Instruct	—	93.3	—	evidence
Qwen2.5-Coder 32B Instruct	—	92.7	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite HumanEval?

HumanEval