BlogLLM Benchmark Scores as Published, Side by Side
DROP: Results as Published
Every result the catalog holds for DROP: 12 models from 5 developers, read from 3 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 General Knowledge and ReasoningMaintainer Allen Institute for AI and UC Irvine (Dheeru Dua and co-authors)Introduced 2019Data version 2026103001, as of 2026-10-30
DROP tests reading comprehension that needs discrete reasoning over a paragraph: resolving references, then adding, counting, comparing or sorting what the paragraph says. The score is a token-level F1 between the answer and the reference, printed as a percentage.
DROP (F1)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| o1OpenAI, released 2024-12-17 | 90.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| o1-miniOpenAI, released 2024-09-12 | 83.9% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| GPT-4oOpenAI, released 2024-05-13 | 83.7% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Claude 3.5 SonnetAnthropic, released 2024-10-22 | 88.3% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 88.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 88.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 1 more page | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 88.2% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-R1DeepSeek, released 2025-01-20 | 92.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| DeepSeek-V3DeepSeek, released 2024-12-26 | 91.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Kimi K2 BaseMoonshot AI, released 2025-07-11 | 83.6% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 3-shot |
| MiMo-V2.5 BaseXiaomi, released 2026-04-27 | 83.7% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 3-shot |
| MiMo-V2.5-Pro BaseXiaomi, released 2026-04-27 | 86.3% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 3-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.