readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

reasoning · closed weights · Sep 25, 2025

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) has a Quality Score of 19.5, ranking 399th among 551 scored models. Per 1M tokens, pricing is $0.100 input, $0.400 output, and $0.010 cached input. It has a 1M token context window. Its Reliability Score is 23.0, ranking 413th among 553 scored models, below average (total average: 35.6). Its Value Score is 18.0, low compared with the total Value average of 30.7.

Quality Score19.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.0
Factual reliability23.0
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.100
Output
$0.400
Cached Input
$0.010
Cache write
not available
Cost per task
not available

Capability

Intelligence
10.4
Coding
not available
Agentic
not available
Omniscience
-54.0
Correct
18.0%
Blended price
$0.067

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.0%

Correct 18.0%Incorrect 72.0%Partial / not attempted 10.0%

Artificial Analysis benchmarks

Humanity’s Last Exam
7%
GPQA Diamond
71%
CritPt
0%
AA-Omniscience
23%
AA-LCR
65%

Similar models

Support me! Patreon