Gemini 1.5 Pro

Gemini 1.5 Pro

Gemini 1.5 Pro handles infinite context with 99% retrieval accuracy at 750k tokens via Mixture-of-Experts and generates chapter summaries for 2-hour videos with 92% accuracy.

ConversationReasoningAnalysisCode Generation
Provider
Google
Release Date
February 15, 2024
Size
LARGE
Parameters
~1.2T

Benchmark Performance

Performance metrics on industry standard AI benchmarks that measure capabilities across reasoning, knowledge, and specialized tasks.

MMLU

86.0%

MATH

67.7%

GPQA

46.2%

HumanEval

71.9%

MGSM

88.7%

Berkeley Function Calling (BFCL)

84.4%

Model Insights

All Model Responses

No responses available for this model yet.