readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 3.8 Flash (high)

reasoning · closed weights · Sep 2, 2026

Gemini 3.8 Flash (high) has a Quality Score of 72.4, ranking 13th 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 64.8, ranking 13th among 275 scored models, above average (total average: 34.4). Its Value Score is 55.4, high compared with the total Value average of 28.6.

Quality Score72.4coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1
Value Score55.4
Reliability64.8
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
$0.577

Capability

Intelligence
58.7
Coding
76.3
Agentic
50.0
Omniscience
29.6
Correct
54.6%
Blended price
$0.578

Answer outcomes

Attempt rate: 79.7%

Correct 54.6%Incorrect 25.1%Abstained 20.3%

Artificial Analysis benchmarks

GDPval-AA v2
52%
τ³-Banking
45%
Terminal-Bench v2.1
88%
SciCode
54%
Humanity’s Last Exam
48%
GPQA Diamond
95%
CritPt
18%
AA-Omniscience
65%
AA-LCR
81%

Similar models