Yandex AliceAI Cards - BigCodeBench (1-shot): leaderboard
BigCodeBench library-heavy Python tasks in Yandex's own implementation with improved tests, 1-shot. Yandex AliceAI-Foundation-80B-A3B-Base model card (September 2026); pretrained base checkpoints, greedy decoding; pass@1 in percent, higher is better.
Metric: Pass@1 (%). Source: huggingface.co. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 35B A3B Base | 43.5 | #319 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=yandex-aliceai-cards-bigcodebench-1-shot · How It Works · Data refreshed daily, snapshot 2026-11-07.