Release68d ago
Cohere boosts Command R+ code tool-use with nested multi-level JSON schema support and automatic retry loops
Enterprise AI platform Cohere hardened tool-use capabilities in Command R+. For intricate CI/CD pipelines and cloud orchestration, the model now natively handles deeply nested (5+ levels) JSON schemas with self-correcting retry loops upon parameter validation failure, cutting enterprise workflow aborts by 75%.
Release12d ago
NVIDIA open-sources Nemotron 3.5 Bolt E4B 4GB, a Gemma 4 E4B-based small model for local assistants, characters and robots with tool use
On 2026-10-23 (15:41 UTC) the official @NVIDIAAI account announced Nemotron 3.5 Bolt E4B 4GB, a small open model for local assistants, interactive characters and robots that can hold a conversation and use tools. The official Hugging Face model card says it is post-trained from Gemma-4-E4B-it, has 8B total parameters (4B effective), ships in Q4_K_M quantization, supports up to 64K input and 64K output tokens, and has a switchable thinking mode, plus a DFlash speculative-decoding drafter and a BF16 version. Weights, data and recipes are open under the OpenMDW-1.1 license, with commercial use allowed. On the model card the 4GB build scores 55.60 on MultiChallenge (Gemma4 E4B-it at the same quantization 39.36, Qwen3.5 4B 52.23), but trails Qwen3.5 4B on Tau2-Bench (52.32) and BFCL-v3 (67.31).
Models33d ago
Cohere Embed 5 ships: Pro/Fast shared space; ViDoRe V3 Pro 85.8 avg; Fast at $0.08/M tokens
On 2026-09-30 Cohere launched Embed 5 with Pro and Fast tiers that share one embedding space (index with Pro, query with Fast). Multimodal text/image/fused inputs, 128K context, 100+ languages; API ids embed-v5.0-pro / embed-v5.0-fast. Blog: ViDoRe V3 Pro avg 85.8 (+8.8 vs Embed 4); text pricing $0.12 / $0.08 per M tokens. Available on Cohere API, Model Vault, Azure Foundry, SageMaker; vLLM for private deploy.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.