AI Benchmark Model

Gemini 3.7 Flash (medium)

Benchmark scores, pricing, speed, and model comparisons for Gemini 3.7 Flash (medium).

Key scores

Intelligence53.4Index score
Coding71.5Index score
Speed347.8Tokens/sec
Blended Cost$1.50Per 1M tokens

Gemini 3.7 Flash (medium) is an AI model released by Google on August 13, 2026. This model achieves an intelligence index of 53.4 and a coding index of 71.5. Performance metrics indicate an output speed of 347.826 tokens per second with a time to first token of 3.87 seconds. Regarding benchmark results, the model scores 0.921 on GPQA, 0.39 on HLE, 0.579 on SciCode, and 0.81 on LCR. Pricing for the model is set at $0.75 per 1 million input tokens and $3.75 per 1 million output tokens, resulting in a blended cost of $1.50 per 1 million tokens. The math index for this specific model version remains unknown.

Benchmark results

4 tracked benchmark rows for Gemini 3.7 Flash (medium).

GPQA Reasoning
92.1%
LCR Other
81.0%
SciCode Other
57.9%
HLE Other
39.0%

Comments (0)

No comments yet

Be the first to share your thoughts!