BlogLLM Benchmark Scores as Published, Side by Side
CorpusQA: Results as Published
Every result the catalog holds for CorpusQA: 6 models from 4 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 Long ContextMaintainer Alibaba Tongyi Lab (Zhiyuan Lu and co-authors)Introduced 2026Data version 2026103001, as of 2026-10-30
CorpusQA tests reasoning over whole document collections: the evidence for a question is spread over hundreds of files, and the answer needs comparison or aggregation rather than lookup. Inputs scale up to about 10 million tokens; publishers usually print the 1 million token setting as accuracy.
CorpusQA 1M
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Opus 4.6Anthropic, released 2026-02-05 | 71.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max; Context: 1M |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 53.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Context: 1M |
| DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-24 | 59.3% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Context: 1M |
| 15.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: non-think; Context: 1M | |
| 60.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max; Context: 1M | |
| DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-24 | 56.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Context: 1M |
| 35.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: non-think; Context: 1M | |
| 62% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max; Context: 1M |
CorpusQA (AI-judge score)
AI-judge score
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 79 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | Effort: max |
| MAI-Thinking-1Microsoft, released 2026-08-12 | 82 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | Effort: max |
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.