Skip to content

Benchmark

BFCL-V4

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
24
Scores recorded
28
Sources
2
IQ weight
1.55

Score distribution

63.6%
Mean
67.7%
Median
11.3%
Std dev
52.4%
10th percentile
73%
90th percentile
25.3%
Min
25.3%75%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.55 for chat models, measured over 24 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75%
2Qwen3.7 MaxQwen3.7-Max release · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75%
3GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official BFCL V4 harness commit 6ea5797 · 5,217 cases · temperature 0.001 · weighted overall score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.1%
4Ling 3.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73%
5Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
6Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.9%
7Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
8Qwen3.7 PlusQwen3.7-Plus release · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.9%
9Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
10DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official BFCL V4 harness commit 6ea5797 · 5,217 cases · temperature 0.001 · weighted overall score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.4%
11Trinity Large ThinkingTrinity-Large-Thinking Model Card · card row is misspelled ‘BCFLv4’· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.1%
12Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official BFCL V4 harness commit 6ea5797 · 5,217 cases · temperature 0.001 · weighted overall score· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.1%
13Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.5%
14Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.7%
15Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.3%
16Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.1%
17Qwen3.5 Omni PlusQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.3%
18Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.4%
19Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.3%
20Nova 2 LiteAmazon Nova 2 Lite official launch chart / technical report · Overall FC, v1· Reported by Amazon Web Services, Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.3%
21Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.2%
22LFM2.5 2.6B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.9%
23Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.3%
24Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.4%
25Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.4%
26Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50.3%
27Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.6%
28Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim25.3%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats