Gemini 1.5 Pro (Sept 2024)
#154 of 274 scored.
GoogleSep 24, 2024Closed
Capabilities Index
Range 127.2–133.1
131.7
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond43.0%
119th of 186
- ARC-AGI-20.8%
68th of 79
- Humanity's Last Exam0.0%
36th of 40
- Mock AIME23.0%
126th of 176
Everything else Epoch has for it
- MMLU82.5%
- MATH level 570.4%
- CadEval34.0%
- DTBench31.6%
- WeirdML22.2%
- Balrog21.0%
- SimpleBench12.5%
- The Agent Company3.4%
On the index
Around it.
Sources