Skip to content

Benchmark

COLLIE

Scores are percentages.

Models measured
11
Scores recorded
11
Sources
1
IQ weight
0.83

Score distribution

76.6%
Mean
72.3%
Median
19.7%
Std dev
54.6%
10th percentile
98.7%
90th percentile
42.5%
Min
42.5%99%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.83 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim99%
2o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim98.7%
3OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim98.4%
4Mistral Medium 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.8%
5Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.2%
6GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.3%
7GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.8%
8Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.9%
9GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61%
10GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.6%
11GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.5%

Data credits: Data by LLM Stats