XpertBench
Seed2.0 Pro 64.5% leads since Feb 2026 Fading Models complete expert tasks from more than 140 task types in law, finance, education, humanities and science. Over 200 domain experts wrote the prompts and weighted rubrics.
In-house Seed benchmark built on the Xpert expert platform. Seed1.8 reports scores per field. Rubric grading is assumed to be automatic.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Seed2.0 Pro leads with 64.5% among models released by Apr 2026
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.
The newest model with a score here came out in Apr 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Seed2.0 Pro 64.5%
- 2 Seed2.0 Lite (0428) 56.8%
- 3 Seed1.8 51.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Seed2.0 Pro | 64.5% | Feb 2026 | Model card | |
| 2 | Seed2.0 Lite (0428) | 56.8% | Apr 2026 | Model card | |
| 3 | Seed1.8 | 51.3% | 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 Apr 2026
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 |
|---|---|---|---|
| 28 Apr 2026 | Seed2.0 Lite (0428) | 56.8 | XPert Bench |
| 18 Dec 2025 | Seed1.8 | 51.3 | Mean of XpertBench Law 55.2 / Fin 62.0 / Edu 47.9 / Research 31.4 / Humanities 60.2 |
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 | XpertBench Law 55.2, Fin 62.0, Edu 47.9, Research 31.4, Humanities 60.2, no overall (Table 4) | Capabilities | |
| 14 Feb 2026 | Seed2.0 Pro model card | 64.5 | XPert Bench (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%