readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 3 Pro Preview (high)

reasoning · closed weights · Nov 18, 2025

Gemini 3 Pro Preview (high) has a Quality Score of 50.3, ranking 90th among 551 scored models. Per 1M tokens, pricing is $2.00 input, $12.00 output, and $0.200 cached input. It has a 1M token context window. Its Reliability Score is 57.6, ranking 63rd among 553 scored models, above average (total average: 35.6). Its Value Score is 32.9, around average compared with the total Value average of 30.7.

Quality Score50.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score32.9
Factual reliability57.6
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
$2.00
Output
$12.00
Cached Input
$0.200
Cache write
not available
Cost per task
not available

Capability

Intelligence
28.0
Coding
not available
Agentic
not available
Omniscience
15.3
Correct
55.8%
Blended price
$1.74

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 96.2%

Correct 55.8%Incorrect 40.5%Partial / not attempted 3.8%

Artificial Analysis benchmarks

Humanity’s Last Exam
40%
GPQA Diamond
91%
CritPt
9%
AA-Omniscience
58%
AA-LCR
76%

Similar models

Support me! Patreon