# CorpusQA 1M leaderboard

Reasoning benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/reasoning-corpus-qa1m

Every model the catalog carries a published CorpusQA 1M value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Reasoning |
| Measure | Long-context QA accuracy |
| Tasks | Million-token corpus question answering |
| Difficulty | Million-token long context |
| Published by | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |

A million-token CorpusQA long-context question-answering benchmark reported in DeepSeek-V4 model evaluations.

## CorpusQA 1M ranking

3 models with a published CorpusQA 1M value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Long-context QA accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 62.0 | Observed 2026-11-21 · source benchlm:models |
| 1 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 62.0 | Last good 2026-11-18 · source benchlm:models |
| 3 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 60.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
