BlogLLM Benchmark Scores as Published, Side by Side
GSM8K: Results as Published
Every result the catalog holds for GSM8K: 6 models from 3 developers, read from 2 pages. 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 OpenAI (Karl Cobbe and co-authors)Introduced 2021Data version 2026103001, as of 2026-10-30
GSM8K tests multi-step arithmetic reasoning with about 8,500 grade-school math word problems. The score is the share of problems with the correct final answer, usually with a stated number of few-shot examples.
GSM8K
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 90.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 92.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 91.1% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| Kimi K2 BaseMoonshot AI, released 2025-07-11 | 92.1% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 8-shot |
| MiMo-V2.5 BaseXiaomi, released 2026-04-27 | 83.3% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 8-shot |
| MiMo-V2.5-Pro BaseXiaomi, released 2026-04-27 | 99.6% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 8-shot |
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.