InclusionAI Ling 3.1 Flash Base Release - CruxEval (1-shot): leaderboard
Official BF16 WSM base-checkpoint comparison; 1-shot; native Pass@1. No instruction/chat or dated 1019 model substitution. LCBench/LCBench-cn use January 2023-February 2025. Evaluation prompt details beyond shot configuration are unpublished. Metric: Pass@1 (%).
Metric: Pass@1 (%). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ling 3.1 Flash Base | 80.5 | |
| 2 | MiMo V2.5 Pro Base | 71.25 | |
| 3 | DeepSeek V4 Pro Base | 69.06 |
Interactive version: theaggregate.ai/benchmark?slug=inclusionai-ling-3-1-flash-base-release-cruxeval-1-shot · How It Works · Data refreshed daily, snapshot 2026-10-28.