Skip to content

Benchmark

ZebraLogic

Scores are percentages.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
0.38

Score distribution

90.2%
Mean
89.3%
Median
5.2%
Std dev
86.8%
10th percentile
95.5%
90th percentile
80.1%
Min
80.1%97.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.38 for chat models, measured over 8 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 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.97.3%
2LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.5%
3Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95%
4LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.3%
5Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89%
6Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.5%
7MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.86.8%
8MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.80.1%

Data credits: Data by LLM Stats