# AGIEval leaderboard

Knowledge 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/knowledge-agieval

Every model the catalog carries a published AGIEval value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Exact match |
| Tasks | General academic and professional exam questions |
| Difficulty | General knowledge |
| Published by | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |

A human-centric exam benchmark for general knowledge and reasoning reported in DeepSeek-V4 base-model evaluations.

## AGIEval ranking

1 model with a published AGIEval 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 | Exact match | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Soofi S 30B-A3B](https://modelscale.dev/models/soofi-s-30b-a3b) | Soofi Project | 66.9 | 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.
