Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Search on Humanity's Last Exam (HLE) (test)
Loading...
45.8
Accuracy
Gemini-3-pro
19.176
26.088
33
39.912
May 5, 2026
Accuracy
Updated 28d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini-3-pro
# Samples=?, Training=...
2026.05
45.8
GLM-4.7-357B
# Samples=?, Training=...
2026.05
42.8
GPT-5-High
# Samples=?, Training=...
2026.05
41.7
DeepSeek-V3.2-671B
# Samples=?, Training=...
2026.05
40.8
OpenSeeker-v2-30B-SFT
# Samples=10.6 k, Trai...
2026.05
34.6
RedSearcher-30B
# Samples=?, Training=...
2026.05
34.3
Tongyi DeepResearch
# Samples=?, Training=...
2026.05
32.9
Claude-4.5-Sonnet
# Samples=?, Training=...
2026.05
32
WebSailor-V2-30B-RL
# Samples=?, Training=...
2026.05
30.6
GLM-4.6-357B
# Samples=?, Training=...
2026.05
30.4
DeepSeek-V3.1-671B
# Samples=?, Training=...
2026.05
29.8
OpenAI Deep Research
# Samples=?, Training=...
2026.05
26.6
WebSailor-V2-30B-SFT
# Samples=?, Training=...
2026.05
23.9
OpenAI-o3
# Samples=?, Training=...
2026.05
20.2
Feedback
Search any
task
Search any
task