Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon agentic tasks on HLE Full
Loading...
45.8
Pass@1
Gemini-3.0-Pro
11.168
20.159
29.15
38.141
Mar 29, 2026
Pass@1
Updated 19d ago
Evaluation Results
Method
Method
Links
Pass@1
Gemini-3.0-Pro
Context Management=w/o CM
2026.03
45.8
Claude-4.5-Opus
Context Management=w/o CM
2026.03
43.4
GPT-5.1 High
Context Management=w/o CM
2026.03
42.7
DeepSeek-v3.2
Context Management=Bas...
2026.03
40.8
Tongyi-DR-30B-A3B
Context Management=Bas...
2026.03
32.9
AgentFounder-30B-A3B
Context Management=-
2026.03
31.5
MiroThinker-v1.5-30B-A3B
Context Management=-
2026.03
31
IterResearch-30B-A3B
Context Management=-
2026.03
28.8
OpenAI DeepResearch
Context Management=-
2026.03
26.6
ASearcher-Web-32B
Context Management=-
2026.03
12.5
Feedback
Search any
task
Search any
task