Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Database interaction on AgentBench DB
Loading...
74.3
Task Completion Score (TCS)
Gemini-3-flash
52.876
58.438
64
69.562
May 27, 2026
Task Completion Score (TCS)
Updated 6d ago
Evaluation Results
Method
Method
Links
Task Completion Score (TCS)
Gemini-3-flash
Average Steps (Stp)=4....
2026.05
74.3
GPT-5-mini
Average Steps (Stp)=4....
2026.05
74
DeepSeek-V3.2
Average Steps (Stp)=7....
2026.05
71.3
Qwen3-235B-A22B
Average Steps (Stp)=2....
2026.05
53.7
Feedback
Search any
task
Search any
task