OpenAI (benchmark); Artificial Analysis (evaluation)
Artificial Analysis HealthBench length-adjusted score
Artificial Analysis independently evaluates 5,000 conversations and reports a length-adjusted rubric score.
ModelsModels with a result.6
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.2026
Result and price
6 of 6 results
Results
6 results#ModelResultThe score from the source.
