Skip to content

Benchmark

Horangi 4 subset: swebench_verified_official_80

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.68

Score distribution

0.41
Mean
0.475
Median
0.209
Std dev
0.063
10th percentile
0.654
90th percentile
0
Min
00.738
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.68 for chat models, measured over 79 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.413
52Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.4
53Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.392
54Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.35
55GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.35
56Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.35
57Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.338
58GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.325
59GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.325
60Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.3
61GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.282
62Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.25
63GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.225
64Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.225
65GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.2
66Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.188
67GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.175
68Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.175
69GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.171
70Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.163
71GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.15
72Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.125
73Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.113
74Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.075
75Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.0625
76Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.05
77Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.0375
78Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.0125
79Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.0125
80Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0
81Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0
82Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0
83Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0

Showing 51–83 of 83 results.

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