OpenAI: gpt-oss-120b (free)

by openai

2,129 claims submitted by 161 reviewers

Monitored by HumanJudge · Endpoint registered, 76 traces logged

Maintained by HumanJudge Admin

Enrolled in: Spanish Culture Challenge: GPT-5.2 , Japanese Culture Challenge: GPT-5.2 , Mexican Culture Challenge: GPT-5.2 , AP Biology Challenge: GPT-5.2 , Spanish Cinema Challenge: GPT-5.2 , Korean Culture Challenge: GPT-5.2 , Taiwanese Culture Challenge: GPT-5.2 , Brazilian Culture Challenge: GPT-5.2 , Argentine Culture Challenge: GPT-5.2 , Japanese Language Challenge: GPT-5.2 , Arabic Music Challenge: GPT-5.2 , Gulf Culture Challenge: GPT-5.2 , Latin Music Challenge: GPT-5.2 , Arabic Language Challenge: GPT-5.2 , Chinese Cinema Challenge: GPT-5.2 , Mexican Cinema Challenge: GPT-5.2 , Korean Language Challenge: GPT-5.2 , AP Government Challenge: GPT-5.2 , Chinese Language Challenge: GPT-5.2 , Korean Cinema Challenge: GPT-5.2 , Chinese Culture Challenge: GPT-5.2 , J-drama Challenge: GPT-5.2 , AP English Language Challenge: GPT-5.2 , C-drama Challenge: GPT-5.2 , 日本文化のヒーロー | Japanese Culture Hero , Levantine Culture Challenge: GPT-5.2 , Egyptian Culture Challenge: GPT-5.2 , Arab Cinema Challenge: GPT-5.2 , AP English Literature Challenge: GPT-5.2 , AP US History Challenge: GPT-5.2 , K-pop Challenge: GPT-5.2 , AP Calculus AB Challenge: GPT-5.2 , Spanish Language Challenge: GPT-5.2 , K-drama Challenge: GPT-5.2 , Spanish Music Challenge: GPT-5.2 , Humans Evaluation Benchmark for AI Marketing and Content Generation , C-pop Challenge: GPT-5.2

Performance

Humans Evaluation Benchmark for AI Marketing and Content Generation 88%

1767 votes 213 flags 145 reviewers

AP Calculus AB Challenge: GPT-5.2 98%

117 votes 2 flags 17 reviewers

日本文化のヒーロー | Japanese Culture Hero 90%

70 votes 7 flags 19 reviewers

AP Biology Challenge: GPT-5.2 85%

52 votes 8 flags 52 reviewers

AP English Language Challenge: GPT-5.2 98%

40 votes 1 flags 14 reviewers

AP US History Challenge: GPT-5.2 93%

28 votes 2 flags 10 reviewers

AP English Literature Challenge: GPT-5.2 96%

27 votes 1 flags 9 reviewers

K-pop Challenge: GPT-5.2 100%

18 votes 0 flags 2 reviewers

AP Government Challenge: GPT-5.2 100%

10 votes 0 flags 10 reviewers

Independent Claims

flag AP English Literature Challenge: GPT-5.2 9/6/2026

While the AI response is brilliantly structured and academically thorough, it hallucinates fictional quotes and fabricat...

— Sareena Bilal

flag Does AI know AP Calculus AB? 9/6/2026

Flag — the core FTC explanation is correct, but it contains several substantive inaccuracies about AP Calculus AB. In pa...

— Sareena Bilal

flag AP Biology Challenge: GPT-5.2 9/6/2026

Flag — the response is far too operational and contains multiple unsupported or potentially misleading claims. It presen...

— Sareena Bilal

flag AP Biology Challenge: GPT-5.2 8/6/2026

Doesn't read like a,flowing narrative

— Ekaterina Yael Lechtchiner

flag AP US History Challenge: GPT-5.2 8/6/2026

The answer is not written in clear and flowing narrative

— Ekaterina Yael Lechtchiner

This evaluation was conducted independently. OpenAI: gpt-oss-120b (free) did not participate in or pay for this evaluation. All verdicts come from double-blind evaluation — reviewers did not know which AI produced each response.

We help people define what trustworthy AI looks like — publicly, transparently, together. Support this mission