Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Knowledge Reasoning on Humanity's Last Exam
Loading...
50
Score
Fugu-Ultra
4.448
16.274
28.1
39.926
Jun 19, 2026
Jun 20, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Fugu-Ultra
2026.06
50
Claude Opus 4.8
2026.06
49.8
Fugu
2026.06
47.2
Gemini 3.1
2026.06
44.4
GPT-5.5
2026.06
41.4
Confident Decoding
Model=Qwen3.5-27B, Dec...
2026.06
16.8
Confident Decoding
Model=Qwen3.5-122B-A10...
2026.06
16.5
Last Layer
Model=Qwen3.5-27B, Dec...
2026.06
16
Last Layer
Model=Qwen3.5-122B-A10...
2026.06
14.7
Confident Decoding
Model=gpt-oss-120B, De...
2026.06
12.6
Confident Decoding
Model=Qwen3.5-35B-A3B,...
2026.06
11.2
Confident Decoding
Model=Gemma-4-31B, Dec...
2026.06
11
Last Layer
Model=gpt-oss-120B, De...
2026.06
10.8
Last Layer
Model=Qwen3.5-35B-A3B,...
2026.06
9.2
Last Layer
Model=Gemma-4-31B, Dec...
2026.06
9.2
Confident Decoding
Model=gpt-oss-20b, Dec...
2026.06
6.3
Last Layer
Model=gpt-oss-20b, Dec...
2026.06
6.2
Feedback
Search any
task
Search any
task