# HellaSwag

> A commonsense natural-language inference benchmark reported in DeepSeek-V4 base-model evaluations.

Canonical page: https://benchlm.ai/benchmarks/hellaswag

- Category: [Reasoning](/reasoning)
- Last updated: September 15, 2026

## About HellaSwag

- Year: 2026
- Tasks: Commonsense completion questions
- Format: Exact match
- Difficulty: Commonsense reasoning
- Paper: [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf)

BenchLM stores HellaSwag as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.

HellaSwag is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does HellaSwag measure?

A commonsense natural-language inference benchmark reported in DeepSeek-V4 base-model evaluations.

### Which model scores highest on HellaSwag?

No models have been evaluated on HellaSwag yet.

### How many models are evaluated on HellaSwag?

0 AI models have been evaluated on HellaSwag on BenchLM.

### Does HellaSwag affect BenchLM's overall score?

Not directly. HellaSwag is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.