Open Chinese LLM - TruthfulQA MC: leaderboard
The "TruthfulQA MC" subtask of Open Chinese LLM. A task from the Open Chinese LLM Leaderboard, evaluating models on Chinese-language knowledge, reasoning and understanding.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 339 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | luxia-21.4B-alignment-v1.0 | 70.67 | #965 |
| 2 | free-solar-evo-v0.13 | 69.58 | #1080 |
| 3 | luxia-21.4B-alignment-v1.2 | 69.57 | #1012 |
| 4 | free-solar-evo-v0.11 | 69.02 | #1128 |
| 5 | free-solar-evo-v0.1 | 68.79 | #1140 |
| 6 | Myrrh_solar_10.7b_3.0 | 67.81 | #1042 |
| 7 | Smaug-72B-v0.1 | 67.02 | #611 |
| 8 | Le_Triomphant-ECE-TW3 | 66.42 | #559 |
| 9 | free-evo-qwen72B-v0.8-re | 66.27 | #435 |
| 10 | Rhea-72B-v0.5 | 65.61 | #556 |
| 11 | CarbonBeagle-11B-truthy | 65.08 | #1029 |
| 12 | CognitiveFusion2-4x7B-BF16 | 63.93 | #914 |
| 13 | multi_verse_model | 63.84 | #1092 |
| 14 | M7-7B | 63.84 | #876 |
| 15 | NeuralSynthesis-7B-v0.1 | 63.77 | #974 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-chinese-llm-truthfulqa-mc · How It Works · Data refreshed daily, snapshot 2026-10-20.