Contamination MapText / LLM / Dataset
HellaSwag
Commonsense sentence-completion (NLI) benchmark of 70k examples built with Adversarial Filtering from ActivityNet Captions and WikiHow contexts; validation and test sets each have 10K examples (5K in-domain, 5K zero-shot categories). HF Rowan/hellaswag: train 39,905 / validation 10,042 / test 10,003.
- Also known as
- HellaSwag
- Domain
- commonsense
- License
- MIT (as stated in the Rowan/hellaswag HF card)
- Homepage
- rowanzellers.com
Exposure by model
| Benchmark | Model | Level | Reason |
|---|---|---|---|
| Classic LLM benchmarks | LLM360 Amber | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | BLOOM | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude 3.5 Sonnet | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude 3.7 Sonnet | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude 3 (Opus, Sonnet, Haiku) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Opus 4 and Claude Sonnet 4 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Fable 5 / Claude Mythos 5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Mythos Preview | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Opus 4.5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Opus 5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Claude Sonnet 5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DCLM-7B-IT (DCLM-IT-7B) | Test data seen | a contamination analysis found test examples in the pre-training data (Overlaps between HellaSwag test examples and DCLM-Baseline pages were detected and removed for an ablation (fraction not reported in text); removal did not lower HellaSwag accuracy (77.9 -> 78.4). In the 10-gram token-overlap analysis HellaSwag is the notable exception with a performance gap between full and 'clean' subsets (Figure 12).) (via DCLM-Baseline 1.0) |
| Classic LLM benchmarks | DCLM-7B (DCLM-Baseline-7B) | Test data seen | a contamination analysis found test examples in the pre-training data (Overlaps between HellaSwag test examples and DCLM-Baseline pages were detected and removed for an ablation (fraction not reported in text); removal did not lower HellaSwag accuracy (77.9 -> 78.4). In the 10-gram token-overlap analysis HellaSwag is the notable exception with a performance gap between full and 'clean' subsets (Figure 12).) (via DCLM-Baseline 1.0) |
| Classic LLM benchmarks | DeepSeek-R1-0528 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-R1-Distill | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-R1 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V3-0324 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V3.1 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V3.2-Exp | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V3.2 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V4.1-Flash | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | DeepSeek-V4 (Pro / Flash) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemini 1.5 (Pro, Flash) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemini 2.5 (Pro, Flash) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemini 3 Pro | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemini 4 Argon | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemma 2 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemma 3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemma 3n | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Gemma 4 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | GPT-4 | Not seen | the authors state its test portion was excluded from training |
| Classic LLM benchmarks | GPT-4o | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | GPT-5.2 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | GPT-5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | GPT-6 Astra | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | gpt-oss | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | InternVL3.5 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Classic LLM benchmarks | InternVL3 | Unknown | unknown for its base model Qwen2.5: training data not disclosed in enough detail |
| Classic LLM benchmarks | LLM360 K2-65B (K2 Diamond) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | K2-Horizon | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | K2-V2 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Llama 2 | Test data seen | a contamination analysis found test examples in the pre-training data (With min. match length L=40: 2,651 of 10,042 samples (26%) 'not clean' (>=20% of tokens in 10+-token n-grams found in pre-training data) and 848 (8.4%) 'dirty' (>=80%); dirty samples scored 92.2 vs 82.5 sampling mean for 70B (Z=7.42). Authors conclude HellaSwag scores appear boosted by contamination, 70B more than 7B.) |
| Classic LLM benchmarks | Llama 3.1 | Test data seen | a contamination analysis found test examples in the pre-training data (85% of HellaSwag examples considered contaminated (8-gram overlap with the pre-training corpus at a dataset-specific token-ratio threshold); estimated performance gain 14.8 / 14.8 / 14.3 points for 8B / 70B / 405B.) |
| Classic LLM benchmarks | Llama 3.2-Vision (11B, 90B) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Llama 3.2 (1B, 3B) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Llama 3.3 70B | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Meta Llama 3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Llama 4 (Scout, Maverick) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | LLaVA-OneVision-1.5 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Classic LLM benchmarks | LLaVA-OneVision | Unknown | unknown for its base model SigLIP: training data not disclosed in enough detail |
| Classic LLM benchmarks | Ministral 3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Mistral 7B | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Mistral Large 3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Mistral Medium 3.5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Mistral Small 4 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Mixtral 8x7B | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Molmo (0924) | Unknown | unknown for its base model OpenAI CLIP: training data not disclosed in enough detail |
| Classic LLM benchmarks | Molmo2 | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Classic LLM benchmarks | OpenAI o1 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | OpenAI o3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | OLMo (February 2024) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | OLMo 2 (November 2024) | Test data seen | a contamination analysis found test examples in the pre-training data (Overlaps between HellaSwag test examples and DCLM-Baseline pages were detected and removed for an ablation (fraction not reported in text); removal did not lower HellaSwag accuracy (77.9 -> 78.4). In the 10-gram token-overlap analysis HellaSwag is the notable exception with a performance gap between full and 'clean' subsets (Figure 12).) (via DCLM-Baseline 1.0) |
| Classic LLM benchmarks | Olmo 3.1 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Olmo 3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Olmo Hybrid 7B | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-3.5 (mini / MoE) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-3 (mini / small / medium) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-4-mini-flash-reasoning | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-4-mini-reasoning | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-4-mini | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-4-reasoning / Phi-4-reasoning-plus | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Phi-4 | Not seen | the authors state its test portion was excluded from training |
| Classic LLM benchmarks | Phi-mini-MoE / Phi-tiny-MoE (SlimMoE) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Pixtral 12B | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Pixtral Large | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Pythia (deduplicated) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Pythia | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen2.5-VL | Unknown | unknown for its base model Qwen2.5: training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen2.5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3-2507 (Instruct-2507 / Thinking-2507) | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3-Next | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3-VL | Unknown | unknown for its base model Qwen3: training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3.5 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3.6 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3.8-Flash-Next | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3.8 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | Qwen3 | Unknown | training data not disclosed in enough detail |
| Classic LLM benchmarks | SmolLM2 | Test data seen | a contamination analysis found test examples in the pre-training data (Overlaps between HellaSwag test examples and DCLM-Baseline pages were detected and removed for an ablation (fraction not reported in text); removal did not lower HellaSwag accuracy (77.9 -> 78.4). In the 10-gram token-overlap analysis HellaSwag is the notable exception with a performance gap between full and 'clean' subsets (Figure 12).) (via DCLM-Baseline 1.0) |
| Classic LLM benchmarks | SmolLM3 | Unknown | training data not disclosed in enough detail |
Notes
Contexts come from WikiHow articles and ActivityNet captions (public web text). The GitHub repo rowanz/hellaswag was blocked by GitHub after a wikiHow DMCA notice (2026-09-14); the HF copy was still online on 2026-10-15. Copies found in public web data by third-party studies: Common Crawl: 1247 of 10042 HellaSwag dev examples (12.4%) flagged as present in Common Crawl (Oct 2020-Oct 2023 window). Dev split, not test.; Llama 1 pre-training corpus: Substantial share of HellaSwag marked contaminated in the Llama 1 pre-training corpus (Figure 3a), with significant estimated performance gain.
Sources
- HellaSwag: Can a Machine Really Finish Your Sentence? (arXiv v1) · paper · retrieved 2026-10-15
- Rowan/hellaswag dataset card · dataset card · retrieved 2026-10-15