Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (Accuracy)
Loading...
84.6
Accuracy
INSTRUCT (BASE)
26.776
41.788
56.8
71.812
Feb 5, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
INSTRUCT (BASE)
Backbone=Qwen3-4B-Inst...
2026.02
84.6
DPO-R1 (ZHANG ET AL., 2025)
Backbone=Qwen3-4B-Inst...
2026.02
84.4
DPO-R1 (HIGH)
Backbone=Qwen3-4B-Inst...
2026.02
84.4
PACE
Backbone=Qwen3-8B-Inst...
2026.02
84.4
DPO-R1 (LOW)
Backbone=Qwen3-4B-Inst...
2026.02
84.2
DPO-R1 (MIDDLE)
Backbone=Qwen3-4B-Inst...
2026.02
84.2
DPO-R1 (LOW)
Backbone=Qwen3-8B-Inst...
2026.02
83.2
DPO-R1 (ZHANG ET AL., 2025)
Backbone=Qwen3-8B-Inst...
2026.02
83.2
DPO-R1 (HIGH)
Backbone=Qwen3-8B-Inst...
2026.02
83.2
DPO-R1 (MIDDLE)
Backbone=Qwen3-8B-Inst...
2026.02
82.4
PACE
Backbone=Qwen3-4B-Inst...
2026.02
82.2
INSTRUCT (BASE)
Backbone=Qwen3-8B-Inst...
2026.02
81.2
DPO-R1 (LOW)
Backbone=Llama-3.1-8B-...
2026.02
37.8
PACE
Backbone=Llama-3.1-8B-...
2026.02
37
DPO-R1 (ZHANG ET AL., 2025)
Backbone=Llama-3.1-8B-...
2026.02
35.8
DPO-R1 (HIGH)
Backbone=Llama-3.1-8B-...
2026.02
35.6
DPO-R1 (MIDDLE)
Backbone=Llama-3.1-8B-...
2026.02
34.8
INSTRUCT (BASE)
Backbone=Llama-3.1-8B-...
2026.02
29
Feedback
Search any
task
Search any
task