Skip to content

Benchmark

EgoSchema

Scores are percentages.

Models measured
9
Scores recorded
9
Sources
1
IQ weight
1.40

Score distribution

70.3%
Mean
71.5%
Median
6%
Std dev
67.2%
10th percentile
76.2%
90th percentile
55.7%
Min
55.7%77.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.40 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
1Qwen2-VL-72B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.9%
2Qwen2.5 VL 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.2%
3GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
4Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.1%
5Gemini 2.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.5%
6Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.4%
7Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.6%
8Gemini 2.0 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.2%
9gemini-1.0-pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.7%

Data credits: Data by LLM Stats