Skip to content

Benchmark

NL2Repo

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
27
Scores recorded
27
Sources
1
IQ weight
1.67

Score distribution

50.4%
Mean
48.1%
Median
9.8%
Std dev
39.8%
10th percentile
61.5%
90th percentile
29.4%
Min
29.4%68.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.67 for chat models, measured over 27 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1DeepSeek V4.1 Flash 1017· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.2%
2ERNIE 5.5 Flash Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.8%
3DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64%
4DeepSeek V4 Pro 0813· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.5%
5MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.2%
6LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.5%
7Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.9%
8GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58%
9DeepSeek V4 Flash Vision Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.7%
10GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.3%
11Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.9%
12DeepSeek V4 Flash 0731· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.2%
13GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.9%
14Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.1%
15Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.1%
16Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47.2%
17Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47%
18Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim45.6%
19Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.7%
20GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.7%
21Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.3%
22MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.1%
23Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41.1%
24MiniMax M2.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.8%
25Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim37.9%
26Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36.2%
27Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim29.4%

Data credits: Data by LLM Stats