MMLU-by-task - TruthfulQA MC2: leaderboard
The "TruthfulQA MC2" subtask of MMLU-by-task. A single MMLU subject, reporting per-task multiple-choice accuracy from the MMLU-by-task leaderboard across a wide range of academic and professional domains.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 1249 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Xwin-LM-70B-V0.1 | 59.86 | #982 |
| 2 | StableBeluga2 | 59.44 | #1078 |
| 3 | Llama 2 70B Chat | 57.31 | #1237 |
| 4 | vicuna-33B-v1.3 | 56.16 | #1347 |
| 5 | WizardLM-70B-V1.0 | 54.81 | #1236 |
| 6 | Llama 2 70B Chat (HF) | 52.8 | #1264 |
| 7 | vicuna-13B | 52.68 | #1469 |
| 8 | internlm-20B | 52.61 | #1296 |
| 9 | falcon-40B Instruct | 52.52 | #1458 |
| 10 | MPT-30B-Chat | 52.42 | #1451 |
| 11 | vicuna-13B-v1.3 | 52.14 | #1447 |
| 12 | MythoMax-L2-13B | 51.97 | #1409 |
| 13 | vicuna-13B-v1.5 | 51.51 | #1392 |
| 14 | Nous-Hermes-13B | 51.5 | #1468 |
| 15 | Vicuna-7B-v1.5-16k | 50.35 | #1491 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-truthfulqa-mc2 · How It Works · Data refreshed daily, snapshot 2026-10-20.