Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-domain Knowledge and Reasoning on HLE (official)
Loading...
42
Exact Match
GPT-5 pro
20.264
25.907
31.55
37.193
Feb 1, 2026
Exact Match
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match
GPT-5 pro
tools=with tools
2026.02
42
ChatGPT Agent
2026.02
41.6
Tendem’s AI agent
human involvement=none
2026.02
39
GPT-5 high
tools=with tools
2026.02
35.2
ChatGPT Deep Research
2026.02
26.6
o3 high
tools=with tools
2026.02
24.3
Perplexity Deep Research
2026.02
21.1
Feedback
Search any
task
Search any
task