Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Opinion Alignment on smartvote
Loading...
73.92
Mean Accuracy
SFT+GRPO
34.4104
44.6677
54.925
65.1823
Mar 1, 2026
Mean Accuracy
Updated 3mo ago
Evaluation Results
Method
Method
Links
Mean Accuracy
SFT+GRPO
Base model=Magistral 24B
2026.03
73.92
icl
Base model=Magistral 24B
2026.03
71.41
SFT+GRPO
Base model=Qwen3 8B
2026.03
71.27
SFT
Base model=Magistral 24B
2026.03
70.83
SFT+GRPO
Base model=Llama 3.1 8B
2026.03
70.53
GRPO
Base model=Magistral 24B
2026.03
68.44
SFT
Base model=Llama 3.1 8B
2026.03
67.23
GRPO
Base model=Qwen3 8B
2026.03
67.04
GRPO
Base model=Llama 3.1 8B
2026.03
66.44
icl
Base model=Qwen3 8B
2026.03
66.09
SFT
Base model=Qwen3 8B
2026.03
65.18
icl
Base model=Llama 3.1 8B
2026.03
63.91
ORPO
Base model=Llama 3.1 8B
2026.03
59.23
random
Base model=Untrained b...
2026.03
50
ORPO
Base model=Qwen3 8B
2026.03
39.02
majority
Base model=Untrained b...
2026.03
37.43
ORPO
Base model=Magistral 24B
2026.03
35.93
Feedback
Search any
task
Search any
task
