AInstein-SWE-Bench

Seed2.0 Pro 47.7% leads since Feb 2026 Fading

Agents fix issues and add features in production scientific code repositories, such as quantum chemistry and astrophysics codes. Fail-to-pass tests in containers check each change.

In-house Seed benchmark. The Seed2.0 model card calls it Ainstain Bench.

Made by ByteDance Seed Released Dec 2025 Scientific code Tasks kept private Last in a launch post Dec 2025 , dropped before it saturated Last model added Mar 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Agent task Many steps in a terminal, browser, desktop, app, game or robot.

Paper

Models scored in lab cards

Launch post lists it, from 1 lab

System cards report it, from 1 lab

Seed2.0 Pro leads with 47.7%

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.

Bars Table

1 Seed2.0 Pro 47.7%
2 Seed1.8 36.7%

#	Model	Score	Setting	Date	Source
1	Seed2.0 Pro	47.7%		Feb 2026	Model card
2	Seed1.8	36.7%		Dec 2025	Model card

2 models have held number one since its release in Dec 2025

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

ByteDance Seed

Lab claims Not tested since Mar 2026

Seed2.0 Pro 47.7%

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 Best so far

Labs headline it less often now, last in Dec 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
18 Dec 2025	Seed1.8	36.7	AInstein-SWE-Bench

2 system cards report it, from 1 lab

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
21 Mar 2026	Seed1.8 model card	36.7	AInstein-SWE-Bench (Table 4)	Capabilities
14 Feb 2026	Seed2.0 Pro model card	47.7	AInstein Bench (Table 13), Ainstain Bench in 3.4	Capabilities

Seed2.0 Pro leads with 47.7%

2 models have held number one since its release in Dec 2025

Scores over time

Labs headline it less often now, last in Dec 2025

2 system cards report it, from 1 lab

More in Coding