GPT-4o (Aug 2024)
#166 of 274 scored.
OpenAIAug 6, 2024Closed
Capabilities Index
Range 123.6–130.7
128.8
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond32.3%
134th of 186
- FrontierMath0.4%
80th of 81
- SimpleQA Verified26.0%
62nd of 77
- Mock AIME6.3%
148th of 176
Everything else Epoch has for it
- MMLU79.1%
- MATH level 553.3%
- METR Time Horizons33.8%
- CadEval26.0%
- Aider polyglot23.1%
- Chess Puzzles8.5%
- SimpleBench1.4%
On the index
Around it.
Sources