readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6.1 Sol (Max)

reasoning · closed weights · Sep 29, 2026

GPT-6.1 Sol (Max) has a Quality Score of 62.8, ranking 22nd among 283 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.100 cached input, and $2.50 cache write. It accepts text, image, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 71.0, ranking 27th among 288 scored models, above average (total average: 48.2). Its Value Score is 41.9, high compared with the total Value average of 29.3.

Quality Score62.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score41.9
Factual reliability71.0
Cache Discount95%

Model specification

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

Token prices USD per 1M tokens

Input
$2.00
Output
$10.00
Cached Input
$0.100
Cache write
$2.50
Cost per task
$1.27

Capability

Intelligence
54.6
Omniscience (native net)
42.0
Correct
61.8%
Blended price
$1.47

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 81.6%

Correct 61.8%Incorrect 19.8%Partial / not attempted 18.4%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1554.9 Elo
AutomationBench-AA
64.9%
private 657-task split from dataset v1.0.6
GDP.pdf
31.0%
FrontierCode v2.0
40.6%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
56.1%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
42.0 native net
HLE-Diamond
58.8%
CritPt v2 Hard
69.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
58.1%

Standalone evaluations

GDPval-AA v2.1
1607.5 Elo

Historical evaluations

SciCode v1.0.1
54.2%
AA Long Context Reasoning v1.1
83.0%
Humanity's Last Exam
52.9%
CritPt
31.7%
FrontierCode
49.1%

Similar models

Support me! Patreon