live
weekly refresh
basedagi.org
benchmark evidence

BFCL Overall

BFCL overall function calling accuracy.

winner on BFCL Overall
direct benchmark result, not a broad vertical composite | source row dated 2026-05-15
scored on 2026-05-15
latest mapped results | top 20
#ModelScoreEvidenceTested
1MoonshotAI: Kimi K2 Thinking
Moonshotai
59.1
model-only
independent_benchmark
2026-05-15
2DeepSeek: DeepSeek V3.2
Deepseek
54.1
model-only
independent_benchmark
2026-05-15
3Google: Gemini 2.5 Flash
Google
50.9
model-only
independent_benchmark
2026-05-15
4OpenAI: o4 Mini
Openai
50.3
model-only
independent_benchmark
2026-05-15
5OpenAI: o3
Openai
48.6
model-only
independent_benchmark
2026-05-15
6OpenAI: GPT-5.2
Openai
45.3
model-only
independent_benchmark
2026-05-15
7OpenAI: GPT-4.1
Openai
39.4
model-only
independent_benchmark
2026-05-15
8Meta: Llama 4 Maverick
Meta Llama
37.3
model-only
independent_benchmark
2026-05-15
9Anthropic: Claude Opus 4.5
Anthropic
33.5
model-only
independent_benchmark
2026-05-15
10Mistral: Mistral Small 4
Mistralai
32.4
model-only
independent_benchmark
2026-05-15
11Meta: Llama 3.3 70B Instruct
Meta Llama
31.9
model-only
independent_benchmark
2026-05-15
12Mistral Large
Mistralai
31.8
model-only
independent_benchmark
2026-05-15
13Google: Gemma 3 27B
Google
29.5
model-only
independent_benchmark
2026-05-15
14Meta: Llama 4 Scout
Meta Llama
28.1
model-only
independent_benchmark
2026-05-15
15Anthropic: Claude Haiku 4.5
Anthropic
25.3
model-only
independent_benchmark
2026-05-15
16Amazon: Nova Pro 1.0
Amazon
25.0
model-only
independent_benchmark
2026-05-15
17Anthropic: Claude Sonnet 4.5
Anthropic
24.9
model-only
independent_benchmark
2026-05-15
what this result means

BFCL overall function calling accuracy.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on BFCL Overall. Broad task pages require independent corroboration before naming a general winner.

source record
category: structured_output
metric: accuracy
matched models: 17
latest source date: 2026-05-15
direction: higher is better
inspect upstream source ->