Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Agentic Performance on ACEBench Agent
Loading...
60
End-to-End Accuracy
Qwen3-14B + ARTIS (Sequential)
8
21.5
35
48.5
Feb 2, 2026
End-to-End Accuracy
Process Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
End-to-End Accuracy
Process Accuracy
Qwen3-14B + ARTIS (Sequential)
Model backbone=Qwen3-1...
2026.02
60
63.3
Qwen3-14B + Weighted BoN
Model backbone=Qwen3-1...
2026.02
55
55.8
Qwen3-14B + ARTIS (Parallel)
Model backbone=Qwen3-1...
2026.02
55
55.6
Qwen3-14B + Sequential Revision
Model backbone=Qwen3-1...
2026.02
50
50
Qwen3-14B
Model backbone=Qwen3-1...
2026.02
45
54.2
Qwen3-8B + ARTIS (Sequential)
Model backbone=Qwen3-8...
2026.02
40
52.1
Qwen3-8B + ARTIS (Parallel)
Model backbone=Qwen3-8...
2026.02
35
43.1
Qwen3-32B + ARTIS (Sequential)
Model backbone=Qwen3-3...
2026.02
35
36.3
Qwen3-32B + ARTIS (Parallel)
Model backbone=Qwen3-3...
2026.02
25
26.3
Qwen3-8B + Sequential Revision
Model backbone=Qwen3-8...
2026.02
20
20
Qwen3-32B
Model backbone=Qwen3-3...
2026.02
20
20
Qwen3-32B + Weighted BoN
Model backbone=Qwen3-3...
2026.02
20
21.3
Qwen3-8B + Weighted BoN
Model backbone=Qwen3-8...
2026.02
15
17.6
Qwen3-32B + Sequential Revision
Model backbone=Qwen3-3...
2026.02
15
25
Qwen3-8B
Model backbone=Qwen3-8...
2026.02
10
14.6
Feedback
Search any
task
Search any
task