HLE (with tools)
Full rankings
5 models tested · sorted by score · includes 5 verified scores
| # | Model | Score |
|---|---|---|
| 1 | 64.7 | |
| 2 | 64.7 | |
| 3 | 58.7 | |
| 4 | 53.3 | |
| 5 | 51.4 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About HLE (with tools)
What does HLE (with tools) measure?
HLE (with tools) is a knowledge benchmark in the BenchGecko catalog. 1 AI models have been tested on it. Scores range from 64.7 to 64.7 out of 100.
Which model leads on HLE (with tools)?
Claude Mythos Preview from Anthropic leads HLE (with tools) with a score of 64.7. The median score across 1 tested models is 64.7.
Is HLE (with tools) saturated?
No · the top score is 64.7 out of 100 (65%). There is still meaningful room for improvement on HLE (with tools).
What makes HLE (with tools) distinctive?
HLE (with tools) is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is HLE (with tools) data refreshed?
BenchGecko pulls updates daily. New model scores on HLE (with tools) appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 5
- Updated
- 2026-04-07
Top on HLE (with tools)
Claude Mythos Preview · 64.7Claude Opus 4.7 · 64.7GPT-5.4 · 58.7Claude Opus 4.6 · 53.3Gemini 3.1 Pro · 51.4More knowledge benchmarks
Same category · related evaluations