Skip to content

Benchmark

BFCL Memory

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

24%
Mean
20.7%
Median
17.7%
Std dev
3.9%
10th percentile
54%
90th percentile
0%
Min
0%73.8%
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
51Gemma 3 27B ITPrompt· Berkeley Function-Calling Leaderboard data13.6%
52Qwen3 8BPrompt· Berkeley Function-Calling Leaderboard data13.1%
53Gemini 2.5 Flash-LitePrompt· Berkeley Function-Calling Leaderboard data12.7%
54Qwen3 14BPrompt· Berkeley Function-Calling Leaderboard data11.2%
55Llama 3.1 8B InstructPrompt· Berkeley Function-Calling Leaderboard data10.8%
56Open Mistral Nemofc· Berkeley Function-Calling Leaderboard data10.3%
57Qwen3 30B A3B InstructPrompt· Berkeley Function-Calling Leaderboard data9.7%
58Gemma 3 4B ITPrompt· Berkeley Function-Calling Leaderboard data8.6%
59Open Mistral NemoPrompt· Berkeley Function-Calling Leaderboard data8.6%
60Qwen3 0.6Bfc· Berkeley Function-Calling Leaderboard data8.6%
61Qwen3 0.6BPrompt· Berkeley Function-Calling Leaderboard data8.4%
62Llama 3.3 70B Instructfc· Berkeley Function-Calling Leaderboard data8.2%
63Llama 4 Scoutfc· Berkeley Function-Calling Leaderboard data8.2%
64Llama 3.2 3Bfc· Berkeley Function-Calling Leaderboard data6.2%
65Qwen3 1.7Bfc· Berkeley Function-Calling Leaderboard data6%
66Claude Sonnet 4.5Prompt· Berkeley Function-Calling Leaderboard data5.4%
67command-r7bfc· Berkeley Function-Calling Leaderboard data5.2%
68GPT 5.2Prompt· Berkeley Function-Calling Leaderboard data3.9%
69Gemma 3 1b itPrompt· Berkeley Function-Calling Leaderboard data3.2%
70Llama 3.2 1B Instructfc· Berkeley Function-Calling Leaderboard data3.2%
71Claude Haiku 4.5Prompt· Berkeley Function-Calling Leaderboard data2.6%
72Nova 2 Litefc· Berkeley Function-Calling Leaderboard data2.4%
73Nova Microfc· Berkeley Function-Calling Leaderboard data2.4%
74Claude Opus 4.5Prompt· Berkeley Function-Calling Leaderboard data1.9%
75Nova Profc· Berkeley Function-Calling Leaderboard data1.9%
76Llama 3.1 Nemotron Ultra 253B v1fc· Berkeley Function-Calling Leaderboard data0%

Showing 51–76 of 76 results.

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