Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge-intensive reasoning on C-Eval
Loading...
90.2
Score
Qwen3.5
82.0776
84.1863
86.295
88.4037
May 12, 2026
Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Score
Qwen3.5
Parameter Count=35BA3B
2026.05
90.2
Qwen3.5
Parameter Count=9B
2026.05
88.2
Qwen3VL
Parameter Count=30BA3B...
2026.05
87.29
SenseNova-U1
Parameter Count=30BA3B...
2026.05
85.89
SenseNova-U1
Parameter Count=8B, Co...
2026.05
84.4
Qwen3VL
Parameter Count=8B, Co...
2026.05
83.88
Gemma4
Parameter Count=26BA4B
2026.05
82.39
Feedback
Search any
task
Search any
task