IntelligentBench

BAGEL-7B-MoT 55.3

BAGEL 55.3 leads

Dropped

Labs’ own numbers All independent runs Include claimed scores

Image editing models complete 350 free-form edits that need reasoning and world knowledge. GPT-4o scores each output from 0 to 2 against a reference image, normalized to 100.

In-house benchmark proposed in the BAGEL paper. Criteria are request fulfillment, visual consistency and knowledge-grounded creativity.

Made by: ByteDance Seed (BAGEL team)
Released: May 2025
Kind: Video generation
Level: Everyday
Scored: Graded by a model
Answers: Open-ended

Last in a launch post: May 2025, dropped before it saturated
Last model added: May 2025
Scores refreshed: November 12th, 2026

Paper arxiv.org

Model scored in lab cards

Launch post lists it, from 1 lab

System card reports it, from 1 lab

BAGEL-7B-MoT leads with 55.3

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

BAGEL leads with 55.3 across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

BAGEL leads with 55.3, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

Bars Table

55.3 BAGEL-7B-MoT

1 BAGEL-7B-MoT 55.3

Source: Labs’ model cards

1 BAGEL CoT 55.3
2 Step1X-Edit 14.9

Source: Official IntelligentBench leaderboard

1 BAGEL CoT 55.3
2 BAGEL-7B-MoT 55.3
3 Step1X-Edit 14.9

Sources: Official IntelligentBench leaderboard and labs’ model cards

#	Model	Score	Setting	Date	Source
1	BAGEL-7B-MoT	55.3		May 2025	Lab model card

#	Model	Score	Setting	Date	Source
1	BAGEL	55.3	CoT		Official leaderboard
2	Step1X-Edit	14.9			Official leaderboard

#	Model	Score	Setting	Date	Source
1	BAGEL	55.3	CoT		Official leaderboard
2	BAGEL-7B-MoT	55.3		May 2025	Lab model card
3	Step1X-Edit	14.9			Official leaderboard

The benchmark's own leaderboard has 4 entries, 2 of them models we track. Switch the scores above to rank them together.

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Source: Labs’ model cards

No launch post has listed it since May 2025

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

ByteDance Seed

Date	Launch post	Score	As the post writes it
May 20, 2025	BAGEL-7B-MoT	55.3	IntelligentBench 44.0 (BAGEL+CoT 55.3)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
May 20, 2025	BAGEL-7B-MoT technical report	55.3	IntelligentBench Score, BAGEL w/ Self-CoT (Table 8). Without CoT 44.9	Capabilities