GPT-4o (Nov 2024)
#165 of 274 scored.
OpenAINov 20, 2024Closed
Capabilities Index
Range 123.6–131.2
128.8
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond30.5%
140th of 186
- SWE-bench Verified31.0%
32nd of 32
- ARC-AGI-20.0%
72nd of 79
- Humanity's Last Exam0.0%
36th of 40
- Mock AIME6.2%
149th of 176
Everything else Epoch has for it
- MMLU84.1%
- Lech Mazur Writing81.8%
- GeoBench71.0%
- MATH level 549.8%
- METR Time Horizons40.8%
- WeirdML25.1%
- Aider polyglot18.2%
- Cybench12.5%
- VPCT10.0%
- GDPval9.9%
- The Agent Company8.6%
- ARC-AGI4.5%
- FrontierMath-2025-02-28-Private0.6%
- GSO-Bench0.0%
On the index
Around it.
Sources