Models

OpenAI

gpt-oss-20B (high)

OpenAIOpenAIUnited States

A 20-billion parameter open-source language model from OpenAI, optimized for high performance. It is designed for strong coding and reasoning capabilities while maintaining fast inference speeds.

CodingReasoningFastCheap
Input / 1M tokens
$0.05
Output / 1M tokens
$0.20
Output tokens/s
258.04
First-token seconds
0.35s
Supported plans
8

Benchmark history

Evaluations

13

TAU2

Measured May 14, 2026Source

Score

0.6

Terminalbench Hard

Measured May 14, 2026Source

Score

0.11

Lcr

Measured May 14, 2026Source

Score

0.31

Ifbench

Measured May 14, 2026Source

Score

0.65

Aime 25

Measured May 14, 2026Source

Score

0.89

Scicode

Measured May 14, 2026Source

Score

0.34

Livecodebench

Measured May 14, 2026Source

Score

0.78

Hle

Measured May 14, 2026Source

Score

0.1

Gpqa

Measured May 14, 2026Source

Score

0.69

Mmlu Pro

Measured May 14, 2026Source

Score

0.75

Artificial Analysis Math Index

Measured May 14, 2026Source

Score

89.3

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

18.5

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

24.5

Plan availability

Products and plans that support this model

2

Discussion

Thinking... Make sure you are connected to GitHub server