Who leads the CommonsenseQA benchmark?

gpt-4o currently leads CommonsenseQA with a score of 85.4 on accuracy.

What is the state-of-the-art score on CommonsenseQA?

The state-of-the-art result on CommonsenseQA is 85.4 (accuracy), achieved by gpt-4o as of 2026.

How many models are tracked on CommonsenseQA?

Codesota tracks 3 models on CommonsenseQA.

When was the CommonsenseQA leaderboard last updated?

The CommonsenseQA leaderboard on Codesota includes results through 2026.

Codesota · Benchmark · CommonsenseQAHome/Leaderboards/CommonsenseQA

Unknown

CommonsenseQA.

Name: CommonsenseQA Benchmark Results
Creator: Unknown
Published: 2026-01-01
License: https://creativecommons.org/licenses/by/4.0/

12,247 multiple choice questions requiring commonsense reasoning about everyday concepts.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

accuracy

Accuracy is the reported evaluation metric for CommonsenseQA. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for accuracyverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

Rank	Model	Trust	Score	Year	Links	Fix
01	gpt-4o Non-API entry from src	unverified	85.4	2026	N/A	Looks wrong?
02	claude-35-sonnet Non-API entry from src	unverified	83.2	2026	N/A	Looks wrong?
03	llama-3-70b Non-API entry from src	unverified	80.9	2026	N/A	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

Submit a Result

← Back to Leaderboards