Yandex AliceAI Cards - GSM8K (CoT): leaderboard
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 35B A3B Base | 90.4 |
| 2 | Qwen3.5-4B-Base | 84.5 |
| 3 | Qwen3.5-2B-Base | 69.5 |
| 4 | Gemma 4 E4B | 58.4 |
Interactive version: theaggregate.ai/benchmark?slug=yandex-aliceai-cards-gsm8k-cot · How It Works · Data refreshed daily, snapshot 2026-09-24.