Versions

1 version · Metric: HLE-Verified Accuracy

Versions of HLE-Verified
VersionReleasedModelsResults
HLE-Verified Full 1,811-item verified setLatestFebruary 15, 202622

Recently reported results: HLE-Verified Full 1,811-item verified set

Latest version: HLE-Verified Full 1,811-item verified set

Recently reported results for HLE-Verified Full 1,811-item verified set
ModelScoreSource
Gemini 3.8 Flash54.9%deepmind.google for Gemini 3.8 Flash on HLE-Verified Full 1,811-item verified set (opens in a new tab)HLE-Verified AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.8 Flash on HLE-Verified Full 1,811-item verified set
Gemini 3.7 Flash53.6%deepmind.google for Gemini 3.7 Flash on HLE-Verified Full 1,811-item verified set (opens in a new tab)HLE-Verified AccuracyReported Model cardGoogle DeepMindSelf-reportedRecord for Gemini 3.7 Flash on HLE-Verified Full 1,811-item verified set