Skip to content

Benchmark

CSimpleQA

Factuality benchmarks measure how often models get facts right. Scores are percentages.

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.19

Score distribution

76.8%
Mean
78.4%
Median
7.2%
Std dev
64.8%
10th percentile
84.3%
90th percentile
64.8%
Min
64.8%84.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.19 for chat models, measured over 5 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 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.3%
2Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83.4%
3Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
4DeepSeek V4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.2%
5DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.8%

Data credits: Data by LLM Stats