readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6.1 Sol (High)

reasoning · closed weights · release date not listed

GPT-6.1 Sol (High) has a Quality Score of 60.4, ranking 32nd 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 has a 1M token context window. Its Reliability Score is 70.5, ranking 31st among 288 scored models, above average (total average: 48.2). Its Value Score is 40.3, high compared with the total Value average of 29.3.

Quality Score60.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score40.3
Factual reliability70.5
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
$2.00
Output
$10.00
Cached Input
$0.100
Cache write
$2.50
Cost per task
$0.591

Capability

Intelligence
50.3
Omniscience (native net)
41.0
Correct
60.4%
Blended price
$1.47

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 79.8%

Correct 60.4%Incorrect 19.4%Partial / not attempted 20.2%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1468.6 Elo
AutomationBench-AA
64.5%
private 657-task split from dataset v1.0.6
GDP.pdf
32.0%
FrontierCode v2.0
36.7%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
51.5%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
41.0 native net
HLE-Diamond
51.9%
CritPt v2 Hard
68.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
46.2%

Standalone evaluations

GDPval-AA v2.1
1521.1 Elo

Historical evaluations

SciCode v1.0.1
55.8%
AA Long Context Reasoning v1.1
82.3%
Humanity's Last Exam
51.4%
CritPt
30.0%
FrontierCode
46.6%

Similar models

Support me! Patreon