readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 3.1 Flash-Lite

reasoning · closed weights · Mar 3, 2026

Gemini 3.1 Flash-Lite has a Quality Score of 32.9, ranking 232nd among 551 scored models. Per 1M tokens, pricing is $0.250 input, $1.50 output, and $0.025 cached input. It accepts text, image, video, audio, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 41.8, ranking 200th among 553 scored models, above average (total average: 35.6). Its Value Score is 27.5, around average compared with the total Value average of 30.7.

Quality Score32.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score27.5
Factual reliability41.8
Cache Discount90%

Model specification

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

Token prices USD per 1M tokens

Input
$0.250
Output
$1.50
Cached Input
$0.025
Cache write
not available
Cost per task
$0.039

Capability

Intelligence
15.6
Coding
not available
Agentic
not available
Omniscience
-16.4
Correct
36.3%
Blended price
$0.217

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 89.0%

Correct 36.3%Incorrect 52.7%Partial / not attempted 11.0%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
10%
SciCode
43%
Humanity’s Last Exam
17%
GPQA Diamond
82%
CritPt
1%
AA-Omniscience
42%
AA-LCR
74%

Similar models

Support me! Patreon