/Tech6h ago

Fable Model Ranks Second on BenchBench Rosetta Fieldwork Benchmark

119254.3K

Original post

rohit@krishnanrohit#715inTech

🚨 Added Fable to BenchBench, it's now the second best behind GPT 5.2. Its benchmark was "Rosetta Fieldwork", a procedurally generated conlang to translate a novel English sentence. Validated cleanly, gold control clean.

It is, unsurprisingly, a very good model! It's the first model to truly pass validation with like a genuinely novel idea, since feedback packet steered most others to "annoying paperwork".

GPT 5.2's genius, the reason it won, was that it had uniform difficulty for all packets. Fable's task turned out to be too easy for Gemini, who are disproportionately gooda t pattern-induction!

rohit@krishnanrohit

http://x.com/i/article/2058941883498553344

3:08 AM · Jun 10, 2026 · 3.7K Views

/Tech6h ago

Fable Model Ranks Second on BenchBench Rosetta Fieldwork Benchmark

119254.3K

#715

Original post

rohit@krishnanrohit#715inTech

It is, unsurprisingly, a very good model! It's the first model to truly pass validation with like a genuinely novel idea, since feedback packet steered most others to "annoying paperwork".

GPT 5.2's genius, the reason it won, was that it had uniform difficulty for all packets. Fable's task turned out to be too easy for Gemini, who are disproportionately gooda t pattern-induction!

rohit@krishnanrohit

http://x.com/i/article/2058941883498553344

3:08 AM · Jun 10, 2026 · 3.7K Views

Sentiment

Users express optimism about Fable's second-place ranking on the BenchBench Rosetta Fieldwork Benchmark because they view it as a smart model likely to improve with another attempt.

Pos

100.0%

Neg

0.0%

1 comments with sentiment.

Cluster Engagement

Posts from X

Most Activity

VIEWS555BOOKMARKS1LIKES6

rohit@krishnanrohit

This is the spread of scores, and why GPT 5.2 is still the winner.

I also think that if we give Fable another shot, given this input, it would probably do better. I haven't done so yet, (sorry, intelligence too expensive to meter). It really is a smart model!

rohit@krishnanrohit

It is, unsurprisingly, a very good model! It's the first model to truly pass validation with like a genuinely novel idea, since feedback packet steered most others to "annoying paperwork".

GPT 5.2's genius, the reason it won, was that it had uniform difficulty for all packets. Fable's task turned out to be too easy for Gemini, who are disproportionately gooda t pattern-induction!

6h55561