readable AI benchmarks

OpenAI

gpt-oss-20b (low)

reasoning · open weights · Aug 5, 2025

Quality Score12.7
Value Score16.2
Reliability20.7
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.070
Output
$0.200
Cached Input
not available
Cached Output
not available
Cost per task
not available

Capability

Intelligence
14.4
Coding
not available
Agentic
not available
Omniscience
-58.5
Correct
15.1%
Blended price
$0.083

Answer outcomes

Correct 15.1%Incorrect 73.6%Abstained 11.3%

Artificial Analysis benchmarks

SciCode
34%
Humanity’s Last Exam
5%
GPQA Diamond
61%
CritPt
0%
AA-Omniscience
21%
AA-LCR
31%

Similar models