Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Expert-Level Question Answering on Humanity's Last Exam
Loading...
40.9
Accuracy
Seed-1.8
16.46
22.805
29.15
35.495
Feb 6, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Seed-1.8
Model Access Type=Clos...
2026.02
40.9
DeepSeek-V3.2
Model Access Type=Clos...
2026.02
40.8
OpenAI-GPT-5-high
Model Access Type=Clos...
2026.02
35.2
Tongyi-DeepResearch 30B
Model Access Type=Open...
2026.02
32.9
Minimax-M2
Model Access Type=Clos...
2026.02
31.8
WebSailor-V2-30B-A3B
Model Access Type=Open...
2026.02
30.6
GLM-4.6
Model Access Type=Clos...
2026.02
30.4
IterResearch-30B-A3B
Model Access Type=Open...
2026.02
28.8
Gemini Deep Research
Model Access Type=Clos...
2026.02
26.9
Kimi-Researcher
Model Access Type=Clos...
2026.02
26.9
Claude-4.5-Sonnet
Model Access Type=Clos...
2026.02
24.5
MiroThinker 8B
Model Access Type=Open...
2026.02
21.5
AgentCPM-Explore-4B
Model Access Type=Open...
2026.02
19.1
Merged-Model-4B
Model Access Type=Open...
2026.02
17.4
Feedback
Search any
task
Search any
task