AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Winogrande
WinoGrande: An Adversarial Winograd Schema Challenge at Scale. A large-scale dataset of 44,000 pronoun resolution problems designed to test machine commonsense reasoning. Uses adversarial filtering to reduce spurious biases and provides a more robust evaluation of whether AI systems truly understand commonsense or exploit statistical shortcuts. Current best AI methods achieve 59.4-79.1% accuracy, significantly below human performance of 94.0%.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Allen Institute for Artificial Intelligence
- Benchmark release
- 2019-11-21
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 22
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| GPT-4 | 0.875 | Not recorded | Not recorded | 2023-06-13 · model_announcement | LLM Stats |
| MiMo-V2.5-Pro | 0.856 | Not recorded | Not recorded | 2026-04-27 · model_announcement | LLM Stats |
| Command R+ | 0.854 | Not recorded | Not recorded | 2024-08-30 · model_announcement | LLM Stats |
| Qwen2 72B Instruct | 0.851 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |
| Llama 3.1 Nemotron 70B Instruct | 0.8453 | Not recorded | Not recorded | 2024-10-01 · model_announcement | LLM Stats |
| Gemma 2 27B | 0.837 | Not recorded | Not recorded | 2024-06-27 · model_announcement | LLM Stats |
| Hermes 3 70B | 0.8319 | Not recorded | Not recorded | 2024-08-15 · model_announcement | LLM Stats |
| Qwen2.5 32B Instruct | 0.82 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Phi-3.5-MoE-instruct | 0.813 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Qwen2.5-Coder 32B Instruct | 0.808 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Gemma 2 9B | 0.806 | Not recorded | Not recorded | 2024-06-27 · model_announcement | LLM Stats |
| Mistral NeMo Instruct | 0.768 | Not recorded | Not recorded | 2024-07-18 · model_announcement | LLM Stats |
| Ministral 8B Instruct | 0.753 | Not recorded | Not recorded | 2024-10-16 · model_announcement | LLM Stats |
| Granite 3.3 8B Base | 0.744 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| Qwen2.5-Coder 7B Instruct | 0.729 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Gemma 3n E4B | 0.717 | Not recorded | Not recorded | 2025-06-26 · model_announcement | LLM Stats |
| Gemma 3n E4B Instructed LiteRT Preview | 0.717 | Not recorded | Not recorded | 2025-05-20 · model_announcement | LLM Stats |
| Phi-3.5-mini-instruct | 0.685 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Phi 4 Mini | 0.67 | Not recorded | Not recorded | 2025-02-01 · model_announcement | LLM Stats |
| Gemma 3n E2B | 0.668 | Not recorded | Not recorded | 2025-06-26 · model_announcement | LLM Stats |
| Gemma 3n E2B Instructed LiteRT (Preview) | 0.668 | Not recorded | Not recorded | 2025-05-20 · model_announcement | LLM Stats |
| ERNIE 4.5 | 0.513 | Not recorded | Not recorded | 2025-06-25 · model_announcement | LLM Stats |