readable AI benchmarks

Google

Gemini 3.6 Flash (high)

reasoning · closed weights · Jul 21, 2026

Quality Score65.0
Value Score48.6
Reliability61.1
Cache Discount80%

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
$0.150
Cached Output
not available
Cost per task
$0.344

Capability

Intelligence
51.6
Coding
69.2
Agentic
40.5
Omniscience
22.1
Correct
50.0%
Blended price
$0.630

Answer outcomes

Correct 50.0%Incorrect 27.8%Abstained 22.2%

Artificial Analysis benchmarks

GDPval-AA v2
46%
τ³-Banking
30%
Terminal-Bench v2.1
78%
SciCode
53%
Humanity’s Last Exam
41%
GPQA Diamond
93%
CritPt
11%
AA-Omniscience
61%
AA-LCR
79%

Similar models