Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple-choice Question Answering on MMLU-Pro (General Accuracy)
Loading...
81.5
Accuracy (MMLU-Pro)
ARMOR-MAD
52.38
59.94
67.5
75.06
Jun 8, 2026
Jun 9, 2026
Jun 10, 2026
Jun 11, 2026
Accuracy (MMLU-Pro)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (MMLU-Pro)
ARMOR-MAD
Agents=gpt-4o-mini, de...
2026.06
81.5
MoA
2026.06
79
Hetero-MAD
Agents=gpt-4o-mini, de...
2026.06
76
Hetero-Vote-only
Agents=gpt-4o-mini, de...
2026.06
71.5
INFUSER
Anchor Model=Qwen3-8B-...
2026.06
66.2
Self-Consistency
Agents=gpt-4o-mini
2026.06
66
SPICE†
Anchor Model=Qwen3-8B-...
2026.06
65
R-Few†
Anchor Model=Qwen3-8B-...
2026.06
63.2
AZR
Anchor Model=Qwen3-8B-...
2026.06
62.32
R-Zero
Anchor Model=Qwen3-8B-...
2026.06
61.82
Single-CoT
Agents=gpt-4o-mini
2026.06
61.5
Base
Anchor Model=Qwen3-8B-...
2026.06
59.91
Homo-MAD
Agents=gpt-4o-mini
2026.06
54
D-MAD
2026.06
53.5
Feedback
Search any
task
Search any
task