Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Tool Use on τ²-Bench Retail
Loading...
90.4
Accuracy
Seed2.0 Pro
66.064
72.382
78.7
85.018
Apr 9, 2026
Apr 22, 2026
May 6, 2026
May 20, 2026
Jun 2, 2026
Jun 16, 2026
Jun 30, 2026
Accuracy
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
Seed2.0 Pro
2026.06
90.4
Claude-Opus-4.5
2026.06
88.9
Claude-Sonnet-4.5
2026.06
86.2
Gemini-3-pro High
2026.06
85.3
Qwen3.5-27B
Architecture=Dense, #...
2026.04
84.7
GPT-5.2 High
2026.06
82
K-EXAONE-236B-A23B
Architecture=MoE, # To...
2026.04
78.6
GPT-5 mini
Reasoning Mode=REASONI...
2026.04
78.3
EXAONE 4.5 33B
Architecture=Dense, #...
2026.04
77.9
Qwen3-VL-235B-A22B
Architecture=MoE, # To...
2026.04
67
Feedback
Search any
task
Search any
task