Skip to content

Benchmark

GeoBench Photos

Models measured
31
Scores recorded
32
Sources
1
IQ weight
1.23

Score distribution

3,556.6
Mean
3,659
Median
498.9
Std dev
2,919
10th percentile
4,204
90th percentile
2,333
Min
2,3334,314
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.23 for chat models, measured over 31 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5high· Epoch AI Benchmarking Hub data4,314
2Claude Fable 5.1high· Epoch AI Benchmarking Hub data4,260
3Gemini 3.8 Flash· Epoch AI Benchmarking Hub data4,251
4Gemini 3 Flash· Epoch AI Benchmarking Hub data4,204
5Muse Spark 1.3· Epoch AI Benchmarking Hub data4,202
6Claude Opus 4.8high· Epoch AI Benchmarking Hub data4,102
7Gemini 3.1 Flash Lite· Epoch AI Benchmarking Hub data3,964
8Gemini 3 Pro Preview· Epoch AI Benchmarking Hub data3,893
9GPT-5.6 Solhigh· Epoch AI Benchmarking Hub data3,881
10Gemini 2.5 Pro· Epoch AI Benchmarking Hub data3,871
11Gemini 3.5 Flash· Epoch AI Benchmarking Hub data3,845
12Gemini 2.5 Pro Preview 05-06· Epoch AI Benchmarking Hub data3,836
13Claude Opus 4.532k· Epoch AI Benchmarking Hub data3,797
14OpenAI o3high· Epoch AI Benchmarking Hub data3,789
15Claude Sonnet 5high· Epoch AI Benchmarking Hub data3,713
16Gemini 2.0 Flash· Epoch AI Benchmarking Hub data3,659
17Claude Sonnet 4.632k· Epoch AI Benchmarking Hub data3,658
18GPT 5medium· Epoch AI Benchmarking Hub data3,498
19gemini-1.5-flash-002· Epoch AI Benchmarking Hub data3,458
20o4 Minihigh· Epoch AI Benchmarking Hub data3,437
21GPT 4o· Epoch AI Benchmarking Hub data3,426
22o1medium· Epoch AI Benchmarking Hub data3,330
23Qwen2.5 VL 72B Instruct· Epoch AI Benchmarking Hub data3,286
24Grok 4.7· Epoch AI Benchmarking Hub data3,185
25Claude Sonnet 3.7· Epoch AI Benchmarking Hub data3,123
26Claude Sonnet 3.715k· Epoch AI Benchmarking Hub data3,027
27Llama 4 Maverick· Epoch AI Benchmarking Hub data2,942
28Grok 4.3· Epoch AI Benchmarking Hub data2,920
29Claude 3.5 Sonnet· Epoch AI Benchmarking Hub data2,919
30Gemma 3 27B IT· Epoch AI Benchmarking Hub data2,857
31GPT-4o mini· Epoch AI Benchmarking Hub data2,831
32Qwen 3.8 27B· Epoch AI Benchmarking Hub data2,333

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)