Skip to content

Benchmark

Horangi 4 subset: humaneval_100

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

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.10

Score distribution

0.916
Mean
0.96
Median
0.134
Std dev
0.83
10th percentile
1
90th percentile
0.13
Min
0.131
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.10 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
1Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs1
2GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs1
3GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs1
4GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
5GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
6GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs1
7GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs1
8Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs1
9Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs1
10Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.99
11Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.99
12Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.99
13Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.99
14Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.99
15GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.99
16GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.99
17GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.99
18GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.99
19GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.99
20Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.99
21Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.99
22Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.98
23Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.98
24Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.98
25Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.98
26GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.98
27Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.98
28Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.98
29Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.98
30Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.979
31Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.97
32Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.97
33GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.97
34Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.97
35Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.97
36Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.96
37Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.96
38Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.96
39GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.96
40GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.96
41GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.96
42Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.96
43Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.96
44GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.96
45Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.95
46GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.95
47Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.94
48Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.94
49Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.94
50Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.94

Showing 1–50 of 83 results.

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