Skip to content

Benchmark

Horangi 4 subset: bfcl

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

Models measured
78
Scores recorded
82
Sources
1
IQ weight
0.00

Score distribution

0.66
Mean
0.678
Median
0.132
Std dev
0.547
10th percentile
0.817
90th percentile
0.302
Min
0.3020.926
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 78 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 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.926
2Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.909
3Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.904
4Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.898
5Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.897
6Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.883
7Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.839
8Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.829
9GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.817
10Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.814
11Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.812
12Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.806
13Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.785
14Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.717
15Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.71
16Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.702
17GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.702
18GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.702
19Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.698
20Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.693
21Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.69
22Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.69
23GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.69
24Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.69
25Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.687
26Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.686
27GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.686
28Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.686
29Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.686
30MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.685
31Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.682
32DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.682
33Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.682
34Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.679
35Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.678
36Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.678
37Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.678
38Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.678
39GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.678
40Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.678
41Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.678
42Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.678
43GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.674
44Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.671
45MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.671
46Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.671
47Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.669
48Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.667
49Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.667
50Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.667

Showing 1–50 of 82 results.

Data credits: Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results