HLE-Verified
We show this table for reference; we do not rank on it.
A verified and revised Humanity's Last Exam set that removes uncertain items and repairs fixable questions before evaluating frontier expert reasoning.
Benchmark score on HLE-Verified — October 17, 2026
We compile the HLE-Verified rows from provider self-reports. Gemini 3.8 Flash leads the table at 54.9%, followed by GPT-5.6 Sol (54.5%) and Claude Opus 5 (54.4%). We do not use these results to rank models overall.
Gemini 3.8 Flash
GPT-5.6 Sol
OpenAI
Claude Opus 5
Anthropic
6 modelsKnowledgeCurrentDisplay onlyUpdated October 17, 2026
Benchmark score table (6 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Gemini 3.8 FlashGoogle | 54.9% | Not reported | Closed |
| 2 | GPT-5.6 SolOpenAI | 54.5% | Not reported | Closed |
| 3 | Claude Opus 5Anthropic | 54.4% | Not reported | Closed |
| 4 | Gemini 3.7 FlashGoogle | 53.6% | Not reported | Closed |
| 5 | GPT-5.6 TerraOpenAI | 51.1% | Not reported | Closed |
| 6 | Claude Sonnet 5Anthropic | 31.0% | Not reported | Closed |
Among the reported HLE-Verified rows, Gemini 3.8 Flash is first at 54.9%. The third row is 0.5 points behind. The broader top-10 range is 23.9 points, so the table still separates the published systems.
6 models have been evaluated on HLE-Verified. The benchmark falls in the Knowledge category. HLE-Verified is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About HLE-Verified
Year
2026
Tasks
1,811 verified or revised expert questions
Format
Full-set accuracy
Difficulty
Frontier multidisciplinary expert reasoning
HLE-Verified contains 1,811 certified items and separates 689 uncertain original HLE items. Google's Gemini 3.8 evaluation reports full-set accuracy as display-only scientific-reasoning evidence; it does not overwrite the existing HLE lanes.
Freshness and provenance
Version
HLE-Verified 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does HLE-Verified measure?
A verified and revised Humanity's Last Exam set that removes uncertain items and repairs fixable questions before evaluating frontier expert reasoning.
Which model scores highest on HLE-Verified?
Gemini 3.8 Flash by Google currently leads with a score of 54.9% on HLE-Verified.
How many models are evaluated on HLE-Verified?
6 AI models have published results on HLE-Verified in the BenchLM catalog.
Compare top models on HLE-Verified
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 5,600+ readers.
One email each week. Unsubscribe anytime.