InclusionAI Ling 3.1 Flash Base Release - CollegeMath (4-shot): leaderboard
Official BF16 WSM base-checkpoint comparison; 4-shot; native Acc. 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 Evaluation prompt details beyond shot configuration are unpublished.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: Accuracy (%).
Metric: Accuracy (%). 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 | 73.41 | |
| 2 | MiMo V2.5 Pro Base | 66.61 | |
| 3 | DeepSeek V4 Pro Base | 63.15 |
Interactive version: theaggregate.ai/benchmark?slug=inclusionai-ling-3-1-flash-base-release-collegemath-4-shot · How It Works · Data refreshed daily, snapshot 2026-10-28.