readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 3.8 Flash (low)

reasoning · closed weights · Sep 2, 2026

Gemini 3.8 Flash (low) has a Quality Score of 66.1, ranking 26th among 275 scored models. Per 1M tokens, pricing is $0.750 input, $3.75 output, $0.075 cached input, and $0.750 cached output. It accepts text, image, video, and speech input, outputs text, and has a 1M token context window. Its Reliability Score is 60.7, ranking 26th among 275 scored models, above average (total average: 34.4). Its Value Score is 49.6, high compared with the total Value average of 28.6.

Quality Score66.1coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1
Value Score49.6
Reliability60.7
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
$0.239

Capability

Intelligence
51.7
Coding
73.5
Agentic
40.8
Omniscience
21.4
Correct
52.2%
Blended price
$0.578

Answer outcomes

Attempt rate: 83.1%

Correct 52.2%Incorrect 30.9%Abstained 16.9%

Artificial Analysis benchmarks

GDPval-AA v2
45%
τ³-Banking
33%
Terminal-Bench v2.1
83%
SciCode
54%
Humanity’s Last Exam
37%
GPQA Diamond
92%
CritPt
4%
AA-Omniscience
61%
AA-LCR
79%

Similar models