Loading…
Loading…
The original long-context Pro model that pioneered Gemini's 2M-token context window and native multimodal input. Now a legacy model, well behind the 2.x and 3.x families on accuracy and speed, retained for backward compatibility.
This model has been retired
Google shut this model down on September 29, 2025. It is no longer available, and the specifications and pricing below are kept for historical reference only.
Every value carries a primary source and a verification date.
Sourced evaluation scores, each verified against its primary source.
GPQA Diamond
GPQA Diamond: 46.2%
SWE-bench Verified
SWE-bench Verified: 22.5%
AIME 2025
AIME 2025: 31.7%
MMLU-Pro
MMLU-Pro: 68.4%
LiveCodeBench
LiveCodeBench: 34.9%