Loading…
Loading…
Legacy Pro model from the Gemini 2.0 generation. Offered a 2M-token context window and strong multimodal reasoning for its era; now superseded by the Gemini 2.5 and 3.x families but retained for compatibility.
Every value carries a primary source and a verification date.
Sourced evaluation scores, each verified against its primary source.
GPQA Diamond
GPQA Diamond: 62.1%
SWE-bench Verified
SWE-bench Verified: 45.8%
AIME 2025
AIME 2025: 58.3%
MMLU-Pro
MMLU-Pro: 78.9%
LiveCodeBench
LiveCodeBench: 49.6%