Benchmark
EgoSchema
Scores are percentages.
All reasoning benchmarksScores from LLM Stats data.
- 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
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
| # | Model | Score |
|---|---|---|
| 1 | Qwen2-VL-72B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.9% |
| 2 | Qwen2.5 VL 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.2% |
| 3 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.2% |
| 4 | Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.1% |
| 5 | Gemini 2.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.5% |
| 6 | Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.4% |
| 7 | Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.6% |
| 8 | Gemini 2.0 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.2% |
| 9 | gemini-1.0-pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.7% |
Data credits: Data by LLM Stats