Satire. Every score on this site is made up. The tweets are real.Read the disclaimer →
Trust Me Bro
Get VerifiedContribute
ModelsBenchmarksIncidentsIn the WildMethodologyChart Crime Studio
TMB-2026-0004··Rumor
🤝🤝🤝Resolved

"Garlic" surpasses the SimpleBench human baseline

Subject: GPT-5.3 (rumored)

Claim

Pre-release: GPT-5.3 "surpasses human baseline on SimpleBench of 83.7%" and "blows every previous model out of the water". "Word has it is a HUGE leap."

Finding

Six months later, Claude Fable 5.1 was widely reported as "the first ever model to beat the human baseline score in SimpleBench". Word, it turns out, did not have it.

Timeline

  1. 22 Feb 2026
    Rumor: human baseline surpassed.@daniel_mac8 · ♥ 1.7K ↗
  2. 3 Sept 2026
    First model reported above the human baseline is a different model.@Lentils80 · ♥ 733 ↗

Primary sources

The posts this entry is based on, embedded as published.

daniel_mac8
Dan McAteer
@daniel_mac8
Link to tweet
GPT-5.3, codenamed "Garlic" 🧄 is released on Thursday, Feb. 26th. It surpasses human baseline on SimpleBench of 83.7%. In fact, it blows every previous model out of the water on all non-coding benchmarks. Word has it is a *HUGE* leap. A GPT-3 to GPT-4 moment again. OpenAI
GPT-5.3, codenamed "Garlic" 🧄 is released on Thursday, Feb. 26th. It surpasses human baseline on SimpleBench of 83.7%. In fact, it blows every previous model out of the water on all non-coding benchmarks. Word has it is a *HUGE* leap. A GPT-3 to GPT-4 moment again. OpenAI https://t.co/GpP5ei1sRE
♥ 1.7KOpen on X ↗
Lentils80
Lentils
@Lentils80
Link to tweet
Claude Fable 5.1 is officially the first ever model to beat the human baseline score in SimpleBench
Claude Fable 5.1 is officially the first ever model to beat the human baseline score in SimpleBench https://t.co/zHnUal8dPl
♥ 733Open on X ↗