BlogLLM Benchmark Scores as Published, Side by Side
OpenScore String Quartets: Results as Published
Every result the catalog holds for OpenScore String Quartets: 2 models from 1 developer, 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 Multimodal UnderstandingMaintainer Dongmin Kim, Brian Liu, Jose J. Valero-Mas and Dasaem JeongIntroduced 2026Data version 2026103001, as of 2026-10-30
This benchmark tests optical music recognition: whether software can read a page of sheet music and write it out in a machine-readable notation. It uses string quartet scores, where several instrument parts play together, with 116 scores from the OpenScore corpus paired with scanned editions from IMSLP. The score is one minus OMR-NED, a normalised edit-distance measure of how far the transcription is from the correct one, so higher is better.
OpenScore String Quartets (1 - OMR-NED)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.84 | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.19 | OpenAI, GPT-6 Astrachecked 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.