Open LLM Leaderboard v1 - HellaSwag: leaderboard
Original Hugging Face Open LLM Leaderboard commonsense sentence completion: HellaSwag with 10 demonstrations and answer-length-normalized multiple-choice accuracy. Percentage, higher is better. Frozen v1 evaluation archive; public questions and possible training overlap limit comparisons with newer models.
Metric: Normalized accuracy (%) (10-shot). Source: huggingface.co. Saturation forecast: Estimated already saturated. 7252 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LLaMAntino-3-ANITA-8B-Inst-DPO-ITA | 92.75 | #1001 |
| 2 | free-evo-qwen72B-v0.8-re | 91.34 | #442 |
| 3 | Rhea-72B-v0.5 | 91.15 | #555 |
| 4 | luxia-21.4B-alignment-v1.2 | 90.86 | #963 |
| 5 | Le_Triomphant-ECE-TW3 | 90.3 | #564 |
| 6 | DARE_TIES_13B | 89.5 | #856 |
| 7 | Llama-3-SauerkrautLM-8B-Instruct | 89.41 | #893 |
| 8 | MoE_13B_DPO | 89.39 | #857 |
| 9 | CarbonBeagle-11B-truthy | 89.31 | #1023 |
| 10 | Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B | 89.3 | #848 |
| 11 | Smaug-72B-v0.1 | 89.27 | #613 |
| 12 | YamshadowExperiment28-7B | 89.25 | #912 |
| 13 | MixTAO-7Bx2-MoE-v8.1 | 89.22 | #815 |
| 14 | AlphaMonarch-7B | 89.18 | #1044 |
| 15 | NeuralSynthesis-7B-v0.1 | 89.18 | #976 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-llm-leaderboard-v1-hellaswag · How It Works · Data refreshed daily, snapshot 2026-11-07.