Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM Knowledge on GPQA Diamond
Loading...
90.7
Avg@16
Gemini-3-Flash
72.5
77.225
81.95
86.675
Dec 30, 2025
Jan 29, 2026
Feb 28, 2026
Mar 31, 2026
Apr 30, 2026
May 30, 2026
Jun 30, 2026
Avg@16
Updated 24d ago
Evaluation Results
Method
Method
Links
Avg@16
Gemini-3-Flash
Tier=High
2026.06
90.7
Seed2.0 Lite
2026.06
85.1
GPT-5-mini
Tier=High
2026.06
82.1
Seed2.0 Mini
2026.06
79
LongCat-Flash Exp-Chat
Evaluation Mode=Chat
2025.12
75.6
DeepSeek V3.2
Evaluation Mode=Chat
2025.12
75.3
GLM 4.6
Evaluation Mode=Chat
2025.12
74.8
LongCat-Flash Chat
Evaluation Mode=Chat
2025.12
73.2
Feedback
Search any
task
Search any
task