LLaMA 3.2vsgpt-oss-120b

LLaMA 3.2
gpt-oss-120b
Specifications
Parameters
1B/3B117B
Context window
128k
API pricing
Cheapest input
$0.027Cloudflare$0.03CoreWeave
Cheapest output
$0.201Cloudflare$0.17CoreWeave
Benchmarks
BullshitBench v2
11%
SWE-Bench Verified
62.4%
Humanity's Last Exam · no tools
14.9%
Humanity's Last Exam · with tools
19%
GPQA Diamond
80.1%
MMLU
90%
Overview
CompanyMetaOpenAI
Release dateSep 25 2024Aug 5 2025
AccessOpen WeightOpen Weight

Other comparisons

LLaMA 3.2vsClaude Opus 5gpt-oss-120bvsClaude Opus 5LLaMA 3.2vsGemini 3.7 Flashgpt-oss-120bvsGemini 3.7 FlashLLaMA 3.2vsGrok 4.6gpt-oss-120bvsGrok 4.6LLaMA 3.2vsDeepSeek-V4-Pro-0813gpt-oss-120bvsDeepSeek-V4-Pro-0813LLaMA 3.2vsMistral Medium 3.5gpt-oss-120bvsMistral Medium 3.5LLaMA 3.2vsKimi K3gpt-oss-120bvsKimi K3

Frequently asked questions

LLaMA 3.2 and gpt-oss-120b don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 3.2 shipped 314 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

LLaMA 3.2 has 1B/3B parameters, while gpt-oss-120b has 117B.

Direct benchmark comparisons are unavailable — LLaMA 3.2 and gpt-oss-120b don't publish scores on any of the same benchmarks.

LLaMA 3.2 was released by Meta on Sep 25 2024.

gpt-oss-120b was released by OpenAI on Aug 5 2025.