Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Abstract Reasoning on ARC Community
Loading...
63.04
Accuracy
Qwen3 + DIARC
-2.5216
14.4992
31.52
48.5408
Jun 25, 2026
Accuracy
Updated 29d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3 + DIARC
#Params=3.6B
2026.06
63.04
Qwen3 + SFT only
#Params=3.6B
2026.06
58.7
Minitron + DIARC
#Params=6.9B
2026.06
43.48
Minitron + SFT only
#Params=6.9B
2026.06
34.78
Llama-3.2 + DIARC
#Params=2.6B
2026.06
30.43
Llama-3.2 + SFT only
#Params=2.6B
2026.06
23.91
Minitron
#Params=8B
2026.06
6.52
Llama-3.2
#Params=3B
2026.06
2.17
Qwen3
#Params=4B
2026.06
0
Feedback
Search any
task
Search any
task