QuantEval - Knowledge QA (CoT): leaderboard
Metric: Accuracy (%; chain-of-thought prompting). Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 86 |
| 2 | GPT-5 | 83.9 |
| 3 | Qwen 3 14B | 75.9 |
| 4 | Gemini 2.5 Pro | 66.7 |
| 5 | DeepSeek R1 Distill Qwen 14B | 66.7 |
| 6 | Qwen 3 8B | 65.5 |
| 7 | Qwen 3 4B | 64.4 |
| 8 | DeepSeek R1 Distill Llama 8B | 50.6 |
| 9 | Qwen 3 30B A3B | 48.5 |
| 10 | DeepSeek-R1-Distill-Qwen-7B | 42.5 |
| 11 | DeepSeek R1 Distill Qwen 1.5B | 37.2 |
Interactive version: theaggregate.ai/benchmark?slug=quanteval-knowledge-qa-cot · How It Works · Data refreshed daily, snapshot 2026-09-25.