Skip to content

Benchmark

OJBench

Scores are percentages.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
0.89

Score distribution

39.3%
Mean
39.5%
Median
10.3%
Std dev
29.7%
10th percentile
48.7%
90th percentile
27.1%
Min
27.1%60.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.89 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
1Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.6%
2Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.7%
3Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.1%
4Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.5%
5Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36%
6Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim32.5%
7Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim29.7%
8Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim27.1%

Data credits: Data by LLM Stats