TriviaQA Benchmark

Explore score history ↗

TriviaQA is an AI benchmark in the Benchmark Radar catalog.

Released: 2017-05-10
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

TriviaQA results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Gemma 2 27B	—	83.7	—	evidence
Kimi K2 Base	—	85.1	—	evidence
Mistral Small 3 24B Base	—	80.3	—	evidence
Mistral Small 3.1 24B Base	—	80.5	—	evidence
Mistral Small 3.1 24B Instruct	—	80.5	—	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 TriviaQA?

TriviaQA