Primary sourcemarktechpost
View sourceEvent ·Official first-hand
webAI 发布 8.8B 推理模型 TwIL-8B，MATH-500 得分 98.2
webAI 基于 IBM Granite 4.2 8B 后训练出 8.8B 推理模型 TwIL-8B。该模型在 MATH-500 上取得 98.2 分，在 LiveCodeBench 上取得 81.6 分。不过它在知识类基准测试上落后于同规模模型。
Current read
webAI 用 IBM Granite 4.2 8B 调出了个 8.8B 小模型，MATH-500 拿到 98.2，做数学和代码推理的可以看看，但知识问答是短板。
2 sources33° AI heatLast updated 2026/11/4 22:25:05
Evidence
2 sourcesRelated source 1rohanpaul_ai
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.