readable AI benchmarks

OpenAI

gpt-oss-20b (high)

reasoning · open weights · Aug 5, 2025

Quality Score13.3
Value Score17.1
Reliability18.5
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
$0.060
Output
$0.190
Cached Input
not available
Cached Output
not available
Cost per task
$0.025

Capability

Intelligence
15.2
Coding
20.7
Agentic
3.1
Omniscience
-63.0
Correct
16.0%
Blended price
$0.073

Answer outcomes

Correct 16.0%Incorrect 79.0%Abstained 4.9%

Artificial Analysis benchmarks

GDPval-AA v2
3%
τ³-Banking
7%
Terminal-Bench v2.1
14%
SciCode
34%
Humanity’s Last Exam
11%
GPQA Diamond
69%
CritPt
1%
AA-Omniscience
18%
AA-LCR
33%

Similar models