Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Instruction Following on Helpsteer2 Trivial
Loading...
78.22
Accuracy
DeepSeek-V3
70.8464
72.7607
74.675
76.5893
Jan 7, 2026
Accuracy
Retrieval Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Retrieval Rate
DeepSeek-V3
2026.01
78.22
87.8
Qwen3-30B-A3B-Thinking-2507
Parameters=30B, Archit...
2026.01
78.14
97.44
Qwen3-Next-80B-A4B-Thinking
Parameters=80B, Archit...
2026.01
77.94
91.18
QwQ-32B
Parameters=32B
2026.01
76.49
91.11
Qwen3-Next-80B-A3B-Instruct
Parameters=80B, Archit...
2026.01
75.88
82.5
DeepSeek-R1
2026.01
73.61
95.24
Qwen3-30B-A3B-Instruct-2507
Parameters=30B, Archit...
2026.01
72.78
95.67
Qwen2.5-32B-Instruct
Parameters=32B, Type=I...
2026.01
71.13
83.19
Feedback
Search any
task
Search any
task