readable AI benchmarks (simplified)

updated on: Nov 3, 2026, 1:48 AM UTC · 772 models

readable AI benchmarks

Google

Gemini 4 Carbon (Low)

reasoning · closed weights · release date not listed

Gemini 4 Carbon (Low) has a Quality Score of 61.7, ranking 11th among 230 scored models. Per 1M tokens, pricing is $4.00 input, $20.00 output, $0.200 cached input, and $4.00 cache write. It has a 1M token context window. Its Reliability Score is 69.6, ranking 20th among 239 scored models, above average (total average: 46.3). Its Value Score is 37.9, high compared with the total Value average of 28.3.

Quality Score61.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score37.9
Factual reliability69.6
Cache Discount95%

Model specification

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

Token prices USD per 1M tokens

Input
$4.00
Output
$20.00
Cached Input
$0.200
Cache write
$4.00
Cost per task
not available

Capability

Intelligence
53.7
Omniscience (native net)
39.2
Correct
49.2%
Blended price
$2.94

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 59.3%

Correct 49.2%Incorrect 10.0%Partial / not attempted 40.7%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1567.5 Elo
AutomationBench-AA
63.5%
private 657-task split from dataset v1.0.6
GDP.pdf
28.6%
FrontierCode v2.0
29.6%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
62.6%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
39.2 native net
HLE-Diamond
61.9%
CritPt v2 Hard
60.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
61.9%

Similar models

GraphOpen on Artificial Analysis

Support me! Patreon