Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Engineering Reasoning on MMLU-Pro Engineering
Loading...
81
Accuracy
MILES
39.92
50.585
61.25
71.915
Jul 8, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
MILES
Backbone=Qwen3-30B-Ins...
2026.07
81
MILES
Backbone=GPT-4.1, Infe...
2026.07
80
SC
Backbone=GPT-4.1, Infe...
2026.07
78.5
SC
Backbone=Qwen3-30B-Ins...
2026.07
78
ZS-CoT
Backbone=GPT-4.1, Infe...
2026.07
75.5
BoT
Backbone=Qwen3-30B-Ins...
2026.07
75.5
MILES
Backbone=GPT-4.1-mini,...
2026.07
75
ZS-CoT
Backbone=Qwen3-30B-Ins...
2026.07
74.5
SC
Backbone=GPT-4.1-mini,...
2026.07
73.5
DC
Backbone=GPT-4.1, Infe...
2026.07
72
MILES
Backbone=GPT-OSS-20B,...
2026.07
71
BoT
Backbone=GPT-4.1-mini,...
2026.07
70.5
SC
Backbone=GPT-OSS-20B,...
2026.07
70
ZS-CoT
Backbone=GPT-OSS-20B,...
2026.07
68.5
DC
Backbone=GPT-4.1-mini,...
2026.07
67.5
BoT
Backbone=GPT-4.1, Infe...
2026.07
67.5
DC
Backbone=GPT-OSS-20B,...
2026.07
66.5
ZS-CoT
Backbone=GPT-4.1-mini,...
2026.07
65.5
DC
Backbone=Qwen3-30B-Ins...
2026.07
52
BoT
Backbone=GPT-OSS-20B,...
2026.07
41.5
Feedback
Search any
task
Search any
task