Yandex AliceAI Cards - GPQA: leaderboard
GPQA graduate-level science questions, 5-shot, run by Yandex; the card does not name the subset. Yandex AliceAI-T5-35B-A0.6B model card (September 2026); pretrained base checkpoints; accuracy in percent, higher is better.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around June 2028. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 35B A3B Base | 47.1 | #705 |
| 2 | Qwen3.5-4B-Base | 38.8 | #2450 |
| 3 | Gemma 4 E4B | 34 | #2249 |
| 4 | Qwen3.5-2B-Base | 31.6 | #6878 |
No result here: #4 Claude Opus 5.5, #5 GPT-6 Astra, #9 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=yandex-aliceai-cards-gpqa · How It Works · Data refreshed daily, snapshot 2026-11-08.