BlogLLM Benchmark Scores as Published, Side by Side
PRBench-Finance: Results as Published
Every result the catalog holds for PRBench-Finance: 5 models from 3 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Knowledge WorkMaintainer Scale AI (Scale Labs)Introduced 2025Data version 2026103001, as of 2026-10-30
PRBench-Finance is the finance half of PRBench, a set of open-ended professional reasoning tasks written by experts holding JDs, CFAs or six or more years of experience, drawn from real professional workflows. The full PRBench has 1,100 tasks, of which 600 are finance, and each answer is scored against expert-written rubric criteria. On the Hard finance subset, the best of 20 models scored only 0.39 at release.
PRBench-Finance
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 55.5 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | Effort: max |
| Claude Fable 5Anthropic, released 2026-06-09 | 55.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 51.9 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 58.3 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.7-MaxAlibaba | 46.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.