QuAC
Llama 3-70B 51.1% Dropped Models answer free-form questions in information-seeking dialogs about a hidden Wikipedia section, across 100K questions. Scored by word-level F1.
In the authors’ words
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at http://quac.ai.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
Llama 3-70B leads with 51.1%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Llama 3-70B 51.1%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Llama 3-70B | 51.1% | Apr 2024 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Apr 2024
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 18 Apr 2024 | Llama 3-70B | 51.1 | QuAC (1-shot, F1) [pretrained] |
12 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 23 Nov 2024 | Llama 3.1-8B technical report | 44.9 | QuAC, pretrained (Table 9) | Capabilities |
| 23 Nov 2024 | Llama 3.1-70B technical report | 51.1 | QuAC, pretrained (Table 9) | Capabilities |
| 23 Nov 2024 | Llama 3.1-405B technical report | 53.6 | QuAC, pretrained (Table 9) | Capabilities |
| 23 Jul 2024 | Llama 3.1-8B model card | 44.9 | QuAC (F1), 1-shot, pretrained (Base pretrained models table) | Capabilities |
| 23 Jul 2024 | Llama 3.1-70B model card | 51.1 | QuAC (F1), 1-shot, pretrained (Base pretrained models table) | Capabilities |
| 23 Jul 2024 | Llama 3.1-405B model card | 53.6 | QuAC (F1), 1-shot, pretrained (Base pretrained models table) | Capabilities |
| 18 Apr 2024 | Llama 3-8B model card | 44.4 | QuAC (1-shot, F1), pretrained (Base pretrained models table) | Capabilities |
| 18 Apr 2024 | Llama 3-70B model card | 51.1 | QuAC (1-shot, F1), pretrained (Base pretrained models table) | Capabilities |
| 19 Jul 2023 | Llama 2-7B technical report | 39.4 | QuAC (f1), 0-shot, pretrained (Table 23) | Capabilities |
| 19 Jul 2023 | Llama 2-70B technical report | 42.4 | QuAC (f1), 0-shot, pretrained (Table 23) | Capabilities |
| 19 Jul 2023 | Llama 2-34B technical report | 42.9 | QuAC (f1), 0-shot, pretrained (Table 23) | Capabilities |
| 19 Jul 2023 | Llama 2-13B technical report | 42.7 | QuAC (f1), 0-shot, pretrained (Table 23) | Capabilities |
More in Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8% - SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9% - WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9% - KMMLU-Pro In use Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry.
Solar Pro 4 79.2% - BIG-Bench Extra Hard In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is a harmonic mean of task accuracies.
Gemma 4 31B IT 74.4% - HLE-Verified In use Verified and revised version of Humanity's Last Exam (1,811 items) with uncertain items removed.
Seed2.0 Pro 73.6%