readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Sol (Non-reasoning)

non-reasoning · closed weights · Sep 22, 2026

GPT-6 Sol (Non-reasoning) has a Quality Score of 45.7, ranking 64th among 282 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.200 cached input, and $2.50 cache write. It has a 872k token context window. Its Reliability Score is 49.6, ranking 69th among 282 scored models, above average (total average: 36.9). Its Value Score is 27.3, around average compared with the total Value average of 30.3.

Quality Score45.7coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score27.3
Reliability49.6
Cache Discount90%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
872k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.00
Output
$10.00
Cached Input
$0.200
Cache write
$2.50
Cost per task
$0.331

Capability

Intelligence
28.1
Coding
not available
Agentic
not available
Omniscience
-0.8
Correct
45.2%
Blended price
$1.54

Answer outcomes

Attempt rate: 91.2%

Correct 45.2%Incorrect 46.0%Abstained 8.8%

Artificial Analysis benchmarks

GDPval-AA v2
36%
SciCode
47%
Humanity’s Last Exam
18%
CritPt
4%
AA-Omniscience
50%
AA-LCR
64%

Similar models

Support me! Ko-Fi