Information Extraction (ByteDance Seed in-house)
Seed2.0 Pro 52% leads since Feb 2026 Fading Models extract words, sentences or fields from meeting records, legal texts, contracts, product descriptions and knowledge bases.
One of six in-house application sets in the Seed1.8 and Seed2.0 model cards. Scoring is a guess.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
Seed2.0 Pro leads with 52%
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.
- 1 Seed2.0 Pro 52%
- 2 Seed1.8 43.7%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Seed2.0 Pro | 52% | Feb 2026 | Model card | |
| 2 | Seed1.8 | 43.7% | 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.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 18 Dec 2025 | Seed1.8 | 43.7 | Information Extraction |
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 | 43.7 | Information Extraction (Table 1) | Capabilities |
| 14 Feb 2026 | Seed2.0 Pro model card | 52 | ToB-Information Extraction (Table 13) | Capabilities |
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
- GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished).
Qwen3.8-Omni-Flash 75.3% - OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%