PIQA Benchmark

Explore score history ↗

PIQA is an AI benchmark in the Benchmark Radar catalog.

Released: 2019-11-27
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

PIQA results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Deepseek v3 base	—	84.7	—	evidence
Gemini 1.5 flash	—	87.5	—	evidence
Gemma 2	—	83.5	—	evidence
GLM 4.5	—	85.3	—	evidence
Phi-3.5-MoE	—	88.6	—	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 PIQA?

PIQA