readable AI benchmarks

Google

Gemini 3.7 Flash (high)

reasoning · closed weights · Aug 13, 2026

Quality Score70.3
Value Score53.5
Reliability63.2
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
$0.402

Capability

Intelligence
56.0
Coding
76.1
Agentic
45.1
Omniscience
26.5
Correct
55.3%
Blended price
$0.578

Answer outcomes

Correct 55.3%Incorrect 28.8%Abstained 15.8%

Artificial Analysis benchmarks

GDPval-AA v2
52%
τ³-Banking
33%
Terminal-Bench v2.1
86%
SciCode
57%
Humanity’s Last Exam
48%
GPQA Diamond
95%
CritPt
14%
AA-Omniscience
63%
AA-LCR
80%

Similar models