Agent Startup Bench

Seed2.1 Pro 68.8% leads since June 2026

In use

Agents complete workflows taken from market-validated AI-native startup products and their users. Domain experts wrote the tasks, attachments and rubrics after user interviews.

In-house Seed benchmark first reported in the Seed2.1 model card. Rubric grading is assumed automatic because the card lists it under automatic evaluation.

Made by: ByteDance Seed
Released: June 2026
Kind: Running a business
Level: Expert
Scored: Graded by a model
Answers: Agent task
Tasks: Kept private

Strongest model tested: GPT-5.5 #20 on the capability index
Last in a launch post: June 2026
Last model added: June 2026
Scores refreshed: November 12th, 2026

Models scored on its own leaderboard

Launch post lists it, from 1 lab

System card reports it, from 1 lab

Seed2.1 Pro leads with 68.8% among models released by June 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Bars Table

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: Official Agent Startup Bench leaderboard

#	Model	Score	Date	Source
1	Seed2.1 Pro	68.8%	Jun 2026	Official leaderboard
2	GPT-5.5	68.1%	Apr 2026	Official leaderboard
3	Claude Opus 4.7	62.3%	Apr 2026	Official leaderboard
4	Doubao Seed 2.1 Turbo	54%	Jun 2026	Official leaderboard
5	Gemini 3.1 Pro	45.7%	Feb 2026	Official leaderboard

Labs report scores for 1 model in their cards. We plot every source in the charts below.

2 models have held number one on the official leaderboard since its release in June 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI ByteDance Seed

Own leaderboard Not tested since Jun 2026

Seed2.1 Pro 68.8%

Source: Official Agent Startup Bench leaderboard

Scores over time

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

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official Agent Startup Bench leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

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
Jun 23, 2026	Seed2.1 Pro	68.8	Agent Startup Bench

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
Jun 23, 2026	Seed2.1 Pro model card	68.8	Agent Startup Bench (Table 1)	Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
Seed2.1 Pro	68.8% Agent Startup Bench	68.8% Leaderboard	Same