Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic on BFCL v4
Loading...
70.64
pass@1
Ling-2.6-1T
30.1424
40.6562
51.17
61.6838
Mar 19, 2026
Apr 2, 2026
Apr 16, 2026
May 1, 2026
May 15, 2026
May 29, 2026
Jun 13, 2026
pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
pass@1
Ling-2.6-1T
2026.06
70.64
GLM-5
Thinking Mode=non-thin...
2026.06
67.57
Qwen3.5 35B-A3B
2026.03
67.3
Ling-2.6-flash
2026.06
66.81
Kimi-K2.5
Mode=Instant
2026.06
62.96
DeepSeek-V3.2
Thinking Mode=nothink
2026.06
60.05
GPT-5.4
Reasoning Mode=non-rea...
2026.06
56.09
Nemotron-3-Nano 30B-A3B
2026.03
53.8
Nemotron-Cascade-2 30B-A3B
2026.03
52.9
GPT-5.4-mini
Evaluation Setting=non...
2026.06
49.72
Qwen3-4B-Thinking-2507
Active / Total Paramet...
2026.05
49.7
Qwen3.5-4B
Active / Total Paramet...
2026.05
45.2
GPT-OSS-120B
Evaluation Setting=low
2026.06
43.3
ZAYA1-8B
Active / Total Paramet...
2026.05
40.5
Nemotron-3-Super 120B-A12B
Evaluation Setting=non...
2026.06
35.12
Gemma-4-E4B-it
Active / Total Paramet...
2026.05
31.7
Feedback
Search any
task
Search any
task