Benchmark
GeoBench AVW
All reasoning benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 1.01
Score distribution
- 3,633
- Mean
- 3,743
- Median
- 572.7
- Std dev
- 2,528
- 10th percentile
- 4,097
- 90th percentile
- 2,528
- Min
This benchmark has a weight of 1.01 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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro· Epoch AI Benchmarking Hub data | 4,097 |
| 2 | Gemini 3.1 Flash Lite· Epoch AI Benchmarking Hub data | 4,057 |
| 3 | Gemini 2.0 Flash· Epoch AI Benchmarking Hub data | 3,743 |
| 4 | GPT 4o· Epoch AI Benchmarking Hub data | 3,740 |
| 5 | Claude Haiku 3.5· Epoch AI Benchmarking Hub data | 2,528 |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)