Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Agent Task Completion on τ-Bench (Retail & Airline Average)
Loading...
18.1
Success Rate (%)
DeepSeek-V3.1
11.652
13.326
15
16.674
Jun 2, 2026
Success Rate (%)
Avg Steps (w/o Clarifier)
Avg Clarify Steps
Total Steps
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (%)
Avg Steps (w/o Clarifier)
Avg Clarify Steps
Total Steps
DeepSeek-V3.1
Clarify Strategy=DeepS...
2026.06
18.1
21
3.9
24.9
None (Full User Intent)
Clarify Strategy=None...
2026.06
18
22.3
0
22.3
Ours (Qwen3-1.7B-trained)
Clarify Strategy=Ours...
2026.06
17.8
23.8
1.3
25.1
Qwen3-30B
Clarify Strategy=Qwen3...
2026.06
17.4
21
3.8
24.8
DeepSeek-R1
Clarify Strategy=DeepS...
2026.06
16.9
20.5
3.9
24.4
Qwen3-14B
Clarify Strategy=Qwen3...
2026.06
16.3
24.2
5.1
29.3
None
Clarify Strategy=None
2026.06
15.4
24.2
0
24.2
Qwen3-8B
Clarify Strategy=Qwen3-8B
2026.06
11.9
23.1
2.7
25.8
Feedback
Search any
task
Search any
task