gpt-oss-120b (high)

OpenAI

ReasoningApache 2.0

Analysis of OpenAI's gpt-oss-120b (high) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Aug 05, 2025
Knowledge Cutoff: May 31, 2024
Window: 131k

PricingPer 1M tokens

Input: $0.15
Output: $0.6
Blended 3:1: $0.2625

Capabilities

Speed: 339 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 0.92 ms
500 token response: 8.30 s

Benchmarks

Reasoning: ●●○○○
Math: ●●●●●
Coding: ●○○○○
MMLU Pro: 80.8%
GPQA: 78.2%
HLE: 18.5%
SciCode: 38.9%
AIME: 93.4%
LiveCodeBench: 87.8%