HellaSwag
About
Commonsense sentence-completion benchmark using adversarially filtered wrong answers. Top LLMs now exceed 95% accuracy.Compare model scores alongside pricing, API availability, and release date — high benchmark score alone doesn't make a model the right pick.
How to read this benchmark
This benchmark uses a scoring system where higher is better. Scores are useful for directional filtering and model shortlisting, not for universal quality ranking.
Interpretation checklist: prefer benchmarks that are closest to your workload style, then validate against the linked model pages for pricing, context window, and provider availability.
Trust when:
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- Model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Don't trust when:
- There is only one benchmark snapshot or the dataset appears stale.
- Benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Current modeled score band for tracked entries is roughly 96.4 – 95.6.
Window
Sep 1 to Mar 6
last 3 snapshots
Mean delta
+2.06
score points
Coverage
47
models in latest snapshot
Leaderboard preview (top 5)
- 1. GPT-4o (05-13)96.4
- 2. Claude 3.5 Sonnet96.2
- 3. Llama 3.1 405B95.8
- 4. DeepSeek V395.7
- 5. Qwen2.5-72B-Instruct95.6