Grok 4.6 takes the #1 spot on InferenceEval 🔥
🥇 Grok 4.6 - 46.9% 🥈 GPT-5.6 Sol - 44.1% 🥉 Opus 5 - 43.0%
It also jumps 5.6 points over Grok 4.5, showing a huge improvement in solving real-world AI inference coding tasks.
AI 导读
Grok 4.6 在 InferenceEval 上拿下第一名 🔥 🥇 Grok 4.6 — 46.9% 🥈 GPT-5.6 Sol — 44.1% 🥉 Opus 5 — 43.0% 相比 Grok 4.5 还提升了 5.6 个百分点，在解决真实世界 AI 推理编码任务方面进步显著。
Grok 4.6 takes the #1 spot on InferenceEval 🔥
🥇 Grok 4.6 - 46.9% 🥈 GPT-5.6 Sol - 44.1% 🥉 Opus 5 - 43.0%
It also jumps 5.6 points over Grok 4.5, showing a huge improvement in solving real-world AI inference coding tasks.
来源：DogeDesigner· x.com