Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction-following clustering on ECHR (C0)
Loading...
85.75
V-measure
o3
40.9676
52.5938
64.22
75.8462
Mar 6, 2026
V-measure
Updated 23d ago
Evaluation Results
Method
Method
Links
V-measure
o3
Model Type=Reasoning M...
2026.03
85.75
Gemini 2.5 Pro
Model Type=Reasoning M...
2026.03
85.05
C1-Qwen-14B
Model Type=Our Model
2026.03
84.05
C1-Qwen-7B
Model Type=Our Model
2026.03
81.81
QwQ-32B
Model Type=Reasoning M...
2026.03
75.98
GPT-oss-120B
Model Type=Reasoning M...
2026.03
70.54
GPT-4.1
Model Type=General Model
2026.03
64.93
Distill-Llama-70B
Model Type=Reasoning M...
2026.03
63.45
GPT-4o
Model Type=General Model
2026.03
58.86
Distill-Qwen-32B
Model Type=Reasoning M...
2026.03
54.43
DeepSeek-R1
Model Type=Reasoning M...
2026.03
53.78
Qwen2.5-72B-Instruct
Model Type=General Model
2026.03
45.57
Llama-3.1-70B-Instruct
Model Type=General Model
2026.03
42.69
Feedback
Search any
task
Search any
task