Stanford + NVIDIA 开源 CLM-8B 对标 Jev
斯坦福与英伟达开源 CLM-8B，用「选动作」替代逐字生成，T-Rex 测试每步 16.5ms 比 Jev 快约 9 倍，但工具调用准确率 95.2% 低于 Jev 的 99.2%。
Stanford + NVIDIA just answered TypeSafe's Jev with CLM-8B. And it's open source. Here's the simple idea: Normal LLMs write answers word by word. That's slow. CLM looks at the situation, looks at the possible actions, and picks the best match. No writing. Just choosing. What the numbers say: ✅ Up to 9x faster than Jev ✅ 16.5 ms per decision vs 149.8 ms for Jev (T-Rex game test) ✅ 13x faster when choosing from ~1,000 options ✅ New best scores on coding agent benchmarks: DeepSWE 81.6%, Terminal-Bench 2.1 87.6% ✅ Free to use — Apache 2.0 weights But let's be fair 👇 Jev was still more accurate in some tests. On tool-calling (BFCL v4), Jev hit 99.2% vs CLM's 95.2%. So CLM wins on speed, not always on accuracy. Why I find this exciting: Only ~20M parameters per head are trained on top of a frozen Qwen3-8B. That means fine-tuning is cheap, and you can run it on your own servers. For anyone building AI agents, this matters. Agents make hundreds of small choices. If each choice is 10x faster, the whole agent feels instant. A bigger multimodal CLM-35B is coming in early October. I'll be watching. Check - https://huggingface.co/Contrastive-LM/CLM-v0.1-8B