CommonsenseQA 2

Models scored

6

Best score

0.68

Metric

Score

CommonsenseQA 2 is an AI evaluation tracked by Epoch AI, with 6 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.

Scored models span January 2022 to July 2023. The best score recorded is 0.68, measured as Score. Models come from OpenAI, Google, Meta AI.

Full record

Score metric: Score
Models scored: 6
Best score recorded: 0.68
Earliest model scored: Jan 27, 2022
Most recent model scored: Jul 18, 2023
Third-party reported: Yes

Leaderboard

01	T5-11B	Google	0.68
02	T5-3B	Google	0.6
03	gpt-3.5-turbo-0613	OpenAI	0.57
04	T5-Large		0.55
05	text-davinci-001	OpenAI	0.53
06	Llama-2-70b-hf	Meta AI	0.5

More benchmarks

Epoch Capabilities Index MMLU Terminal-Bench GPQA Diamond OTIS Mock AIME 2024-2025 GSM8K ARC-AGI ARC-AGI-2

SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.

← All benchmarks