Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Science Reasoning on ARC
Loading...
84.9
Accuracy
GRPO (RLVRR)
79.492
80.896
82.3
83.704
Jan 26, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
GRPO (RLVRR)
#Data=10K
2026.01
84.9
GRPO (RM)
#Data=10K
2026.01
84.2
DPO
#Data=10K
2026.01
83.8
SFT
#Data=10K
2026.01
83.7
Instruct
#Data=n/a
2026.01
83.4
GRPO (GRM)
#Data=10K
2026.01
83.2
GRPO (RLPR)
#Data=10K
2026.01
82.8
GRPO (BLEU)
#Data=10K
2026.01
82
SFT
#Data=100K
2026.01
81.6
GRPO (Random)
#Data=10K
2026.01
79.7
Feedback
Search any
task
Search any
task