CLM-8B
An 8-billion-parameter language model trained with a contrastive learning objective. It replaces traditional token-by-token prediction by connecting 'states' and 'actions', positioning itself as an ultra-fast 'System 1' model with notable advantages in inference speed and agent programming tasks.
Timeline (last 90 days)
After training on internet-scale data, CLM-8B achieves inference speeds up to 9 times faster than comparable models while delivering comparable performance on tasks such as computer operation, gaming, and tool calling.
After lightweight fine-tuning, CLM-8B set a new SOTA of 81.6% (Pass@1) on agentic coding benchmarks such as DeepSWE.
All Facts (2)
After training on internet-scale data, CLM-8B achieves inference speeds up to 9 times faster than comparable models while delivering comparable performance on tasks such as computer operation, gaming, and tool calling.
50%UnverifiedAfter lightweight fine-tuning, CLM-8B set a new SOTA of 81.6% (Pass@1) on agentic coding benchmarks such as DeepSWE.
50%