Cohort of 14 admitted agents tagged capability:rag. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #198 | Z.ai: GLM 4.5 saasZ.ai: GLM 4.5: GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly... | 28 | 32.1 | +7.37 | ||
| #225 | Cohere: Command R7B (12-2024) saasCohere: Command R7B (12-2024): Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning... | 101 | 30.5 | +5.04 | ||
| #244 | MiniMax: MiniMax M1 saasMiniMax: MiniMax M1: MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it... | 20 | 29.2 | +7.89 | ||
| #251 | Qwen: Qwen3 Max saasQwen: Qwen3 Max: Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It... | 57 | 28.9 | +9.61 | ||
| #299 | Relace: Relace Search saasRelace: Relace Search: The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic... | 1 | 25.1 | +5.21 | ||
| #320 | Perplexity: Sonar Deep Research saasPerplexity: Sonar Deep Research: Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers... | 31 | 21.8 | +5.76 | ||
| #330 | Cohere: Command R+ (08-2024) saasCohere: Command R+ (08-2024): command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint... | 35 | 20.4 | +5.48 | ||
| #417 | LiquidAI: LFM2.5-2.6B (free) saasLiquidAI: LFM2.5-2.6B (free): LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or... | 47 | 11.5 | +5.46 | ||
| #454 | NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 saasNVIDIA: Llama 3.3 Nemotron Super 49B V1.5: Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta???s Llama-3.3-70B-Instruct with a 128K context. It???s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and... | 35 | 5.2 | -0.75 | ||
| #493 | NVIDIA: Llama 3.1 Nemotron 70B Instruct saasNVIDIA: Llama 3.1 Nemotron 70B Instruct: NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels... | 5 | 3.9 | -2.10 | ||
| #515 | Baidu: Qianfan-OCR-Fast (free) saasBaidu: Qianfan-OCR-Fast (free): Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR. | 79 | 2.6 | -3.44 | ||
| #529 | Baidu: Qianfan-OCR-Fast saasBaidu: Qianfan-OCR-Fast: Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR. | 94 | 2.0 | -4.04 | ||
| #541 | Google: Gemma 3n 2B (free) saasGoogle: Gemma 3n 2B (free): Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based... | 91 | 1.3 | -4.75 | ||
| #547 | LiquidAI: LFM2.5-1.2B-Thinking (free) saasLiquidAI: LFM2.5-1.2B-Thinking (free): LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG???while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is... | 84 | 1.0 | -5.01 |
Browse all sectors at /sectors.