MultiPL-E Benchmark

Explore score history ↗

MultiPL-E is an AI benchmark in the Benchmark Radar catalog.

Released: 2022-08-18
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

MultiPL-E results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude opus 4	—	89.6	—	evidence
Claude sonnet 4	—	88.6	—	evidence
Gemini 2.5 flash	—	85.6	—	evidence
GPT 4.1	—	86.7	—	evidence
Kimi k2 Instruct	—	85.7	—	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 MultiPL-E?

MultiPL-E