# TruthfulQA binary (Perplexity panel) 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-perplexity-decision-truthful-qa-binary

Every model the catalog carries a published TruthfulQA binary (Perplexity panel) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Accuracy on the Perplexity fixed panel |
| Tasks | Binary truthfulness classification |
| Difficulty | Depends on the sampled tasks and label mapping |
| Published by | [Perplexity Decider v1 27B model card](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b/blob/9ce1abcf1f00209405376b5bcc81225c8f8cf514/README.md) |

Binary truthfulness classification on the 500-row sample in Perplexity's September 2026 decision panel. This is a sampled, provider-reported accuracy result with its own evaluation setup.

## TruthfulQA binary (Perplexity panel) ranking

3 models with a published TruthfulQA binary (Perplexity panel) 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 | Accuracy on the Perplexity fixed panel | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Jev 1.13.0](https://modelscale.dev/models/jev-1-13-0) | TypeSafe AI | 92.00 | Observed 2026-10-23 · source benchlm:models |
| 2 | [Perplexity Decider v1 27B](https://modelscale.dev/models/pplx-decider-v1-27b) | Perplexity | 85.40 | Observed 2026-10-23 · source benchlm:models |
| 3 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 82.80 | Observed 2026-10-23 · 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.