Skip to content

Benchmark

BFCL Web Search

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

Models measured
49
Scores recorded
76
Sources
1
IQ weight
1.16

Score distribution

32.4%
Mean
21%
Median
29.9%
Std dev
1%
10th percentile
77%
90th percentile
0%
Min
0%84.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.16 for chat models, measured over 49 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Qwen3 14Bfc· Berkeley Function-Calling Leaderboard data10%
52GPT-5 miniPrompt· Berkeley Function-Calling Leaderboard data8.5%
53Mistral SmallPrompt· Berkeley Function-Calling Leaderboard data7.5%
54Open Mistral Nemofc· Berkeley Function-Calling Leaderboard data7%
55Nova 2 Litefc· Berkeley Function-Calling Leaderboard data5%
56Phi 4Prompt· Berkeley Function-Calling Leaderboard data4.5%
57Qwen3 4B Instruct 2507Prompt· Berkeley Function-Calling Leaderboard data4.5%
58Gemma 3 12B ITPrompt· Berkeley Function-Calling Leaderboard data4%
59GPT-4.1 miniPrompt· Berkeley Function-Calling Leaderboard data4%
60Llama 3.1 8B InstructPrompt· Berkeley Function-Calling Leaderboard data3%
61Qwen3 4B Instruct 2507fc· Berkeley Function-Calling Leaderboard data3%
62Nova Profc· Berkeley Function-Calling Leaderboard data2.5%
63Open Mistral NemoPrompt· Berkeley Function-Calling Leaderboard data2.5%
64Qwen3 1.7Bfc· Berkeley Function-Calling Leaderboard data2.5%
65GPT-4.1 nanoPrompt· Berkeley Function-Calling Leaderboard data1.5%
66Nova Microfc· Berkeley Function-Calling Leaderboard data1.5%
67Gemma 3 4B ITPrompt· Berkeley Function-Calling Leaderboard data1%
68Llama 3.2 3Bfc· Berkeley Function-Calling Leaderboard data1%
69Qwen3 0.6Bfc· Berkeley Function-Calling Leaderboard data1%
70Granite 3.1 8B Instructfc· Berkeley Function-Calling Leaderboard data0.5%
71Qwen3 0.6BPrompt· Berkeley Function-Calling Leaderboard data0.5%
72Gemini 2.5 Flash-LitePrompt· Berkeley Function-Calling Leaderboard data0%
73Gemma 3 1b itPrompt· Berkeley Function-Calling Leaderboard data0%
74Gemma 3 27B ITPrompt· Berkeley Function-Calling Leaderboard data0%
75Llama 3.1 Nemotron Ultra 253B v1fc· Berkeley Function-Calling Leaderboard data0%
76Llama 3.2 1B Instructfc· Berkeley Function-Calling Leaderboard data0%

Showing 51–76 of 76 results.

Data credits: Berkeley Function-Calling Leaderboard (Gorilla, UC Berkeley), Apache-2.0 (licence)