readable AI benchmarks

Google

Gemini 3.7 Flash (medium)

reasoning · closed weights · Aug 13, 2026

Quality Score68.0
Value Score51.3
Reliability61.9
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image, video, speech
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.750
Output
$3.75
Cached Input
$0.075
Cached Output
$0.750
Cost per task
$0.263

Capability

Intelligence
53.4
Coding
71.5
Agentic
45.1
Omniscience
23.7
Correct
54.0%
Blended price
$0.578

Answer outcomes

Correct 54.0%Incorrect 30.3%Abstained 15.7%

Artificial Analysis benchmarks

GDPval-AA v2
50%
τ³-Banking
35%
Terminal-Bench v2.1
78%
SciCode
58%
Humanity’s Last Exam
39%
GPQA Diamond
92%
CritPt
9%
AA-Omniscience
62%
AA-LCR
81%

Similar models