# GPQA Main Few-Shot (Kaggle) leaderboard

external 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/external-kaggle-gpqa-main-few-shot

GPQA Main Few-Shot (Kaggle benchmark v1). Every model the catalog carries a published GPQA Main Few-Shot (Kaggle) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Accuracy (%) |
| Tasks | 448 main-set questions, few-shot; task version 4 |
| Difficulty | — |
| Published by | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |

Kaggle's few-shot run of the 448-question GPQA main set.

## GPQA Main Few-Shot (Kaggle) ranking

No model in the catalog has a published GPQA Main Few-Shot (Kaggle) score. The benchmark is defined by GPQA: A Graduate-Level Google-Proof Q&A Benchmark, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

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.