BlogLLM Benchmark Scores as Published, Side by Side
CMATH: Results as Published
Every result the catalog holds for CMATH: 3 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 Science and MathMaintainer Tianwen Wei and co-authorsIntroduced 2023Data version 2026103001, as of 2026-10-30
CMATH tests elementary-school math in Chinese with about 1,700 word problems from workbooks and exams across six grades. The score is accuracy, which the paper also reports per grade.
CMath
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 93.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 90.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 92.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
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.