Real-World Finance v2 (Anthropic)
Agents complete 294 long-horizon finance tasks such as building financial models. A model grader compares deliverables pairwise and ratings are fit as Elo.
In-house Anthropic evaluation. Scores are Elo with Sonnet 4.6 fixed at 1000, so they do not compare with the first version.
- 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
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Claude Fable 5 leads with 1,374
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 start at 1,200.
- 1 Claude Fable 5 1,374
- 2 Claude Sonnet 5 1,219
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 1,374 | Jun 2026 | Model card | |
| 2 | Claude Sonnet 5 | 1,219 | Jun 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
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 |
|---|---|---|---|---|
| 30 Jun 2026 | Claude Sonnet 5 system card | 1219 | Real-World Finance v2 Elo, 294 tasks, pairwise Opus 4.8 grader, Sonnet 4.6 anchored at 1000 (8.11.2, Figure 8.11.2.A) | Capabilities |
| 9 Jun 2026 | Claude Fable 5 system card | 1374 | Real-World Finance v2 Elo, 294 tasks, 2,491 pairwise grades, Opus 4.8 grader, Sonnet 4.6 anchored at 1000, labeled Fable/Mythos 5; preferred over Opus 4.8 in 74% of comparisons (8.17.3.1, Figure 8.17.3.1.A) | Capabilities |
More in Law, finance and medicine
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4% - HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items.
Solar Pro 4 77.5% - KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. Solar Pro 4 93.2%
- PRBench In use Model answers 1,100 expert-written law and finance questions. LLM judge grades against weighted expert rubrics of 10-30 criteria each.
Muse Spark 1.3 61.6%