SocialIQa Benchmark

Explore score history ↗

SocialIQa is an AI benchmark in the Benchmark Radar catalog.

Released: 2019-04-23
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

SocialIQa results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Gemini Pro (k-shot, CoT)	—	78.5	—	evidence
GPT-3.5 Turbo (k-shot, CoT)	—	78.0	—	evidence
GPT-4 Turbo (0-shot, SP)	—	82.0	—	evidence
GPT-4 Turbo (k-shot, CoT)	—	84.5	—	evidence
Llama-2-70b (k-shot, CoT)	—	77.5	—	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 SocialIQa?

SocialIQa