Head to head · Open-weight models you run yourself · October 2026 research run
LongCat-2.5 vs Ripple-65B Preview
Ripple-65B Preview scores 53.3 (D) on agent readiness against LongCat-2.5's 50.5 (D), and leads in 2 of 4 scored categories. LongCat-2.5 leads on risk. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons
Which one, for what
Best for Operators with NPU clusters, and anyone tracking what the open flagships can do
Ahead on
- Risk, 60 against 55
Watch for
3,562 GB in BF16 and 1,336 GB at 4 bits
Best for Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.
Ahead on
- Reach, 45 against 35
Watch for
No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reach Ripple-65B Preview +10
LongCat-2.5 35
Memory 0, the smallest build is Meituan's W4A4 repository, 1,336 GB, and 1,336 GB × 1.2 = 1,603 GB, far above 256 GB. The BF16 files are 3,562 GB. Runtimes 0, none of the six runs it in a released version: vLLM 0.33.0, SGLang 0.5.23, Transformers 5.22.2 and llama.cpp b12242 have no LongcatCausalLM or pro_v code, and the model code config.json names isn't in the repository. Builds 10, one quantised build from Meituan, the W4A4 repository (4-bit experts, 1,336 GB). Terms 15, MIT in the metadata, the LICENSE file and the card, with nothing added. Download 10, the Hub API reports gated false for both repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 0 + 0 + 10 + 15 + 10 + 0 = 35.
Ripple-65B Preview 45
Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.
Risk LongCat-2.5 +5
LongCat-2.5 60
File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the meituan-longcat organisation, the name of Meituan's GitHub organisation that the card links for deployment, and the card's licence names Meituan (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions under Usage Considerations: not evaluated for every use, assess accuracy, safety and fairness before sensitive use, and follow the law. Licence risk 15, MIT with no use policy, no threshold and no right to change the terms. Security programme 0, no way to report a flaw on the card beyond a general contact, and Meituan's own security pages weren't looked up, so this scores as absent and is an open question. 25 + 15 + 0 + 5 + 15 + 0 = 60.
Ripple-65B Preview 55
File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.
Score by category
| Category | Weight this run | LongCat-2.5 | Ripple-65B Preview | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 35 | 45 | Ripple-65B Preview +10 |
| Risk | 20%20 | 60 | 55 | LongCat-2.5 +5 |
| Agent interface | 10%10 | 75 | 75 | even |
| Documentation and upkeep | 10%10 | 46 | 49 | Ripple-65B Preview +3 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 50.5/100 | D 53.3/100 |
Facts side by side
| Fact | LongCat-2.5 | Ripple-65B Preview |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Meituan (LongCat) | Ricursive Intelligence |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-11-10 | 2026-11-04 |
| Privacy policy last updated | no document linked | no document linked |
Verdicts
LongCat-2.5
Meituan's flagship is MIT-licensed and documented for tool calling and switchable reasoning, with strong numbers of its own on agentic coding. Almost nobody can run it: 3,562 GB of weights, a 1,336 GB 4-bit build for NPU accelerators, and no released runtime with its architecture. A model to watch until a runtime or a provider picks it up.
Ripple-65B Preview
A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.
Before you call either
LongCat-2.5
- You can't run this on a workstation or a single GPU server. Plan for a provider, and none serves it yet
- If an operator serves it, call it as an OpenAI-compatible chat API with tools in the function format
- Pass
chat_template_kwargswithenable_thinkingtrue or false - With thinking on, keep earlier reasoning in the history (
save_history_reasoning_contenttrue), as the card recommends - The card's results use temperature 1.0 and top_p 0.95
- Its benchmark table is Meituan's own. The unmarked scores are in-house
Ripple-65B Preview
- Run Ricursive's launcher from inference/server with
uv run --script serve.pyon two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default - The launcher turns on
--reasoning-parser rippleand--tool-call-parser ripple; without them tool calls come back as raw text inside tool_call tags - For
tool_choice: "required"setstrict: trueandadditionalProperties: falseon each function, which the README says stopped extra argument fields - Leave room in
max_tokensfor reasoning as well as the answer, since thinking is always on - Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support
Questions
Which is better for AI agents, LongCat-2.5 or Ripple-65B Preview?
Ripple-65B Preview scores 53.3 (D) on agent readiness against LongCat-2.5's 50.5 (D), and leads in 2 of 4 scored categories. LongCat-2.5 leads on risk.
Other comparisons with LongCat-2.5 or Ripple-65B Preview
- Agents-A1-4B vs LongCat-2.5
- Agents-A1-4B vs Ripple-65B Preview
- Apertus v1.5 8B vs LongCat-2.5
- Apertus v1.5 8B vs Ripple-65B Preview
- Apodex-1.1-mini vs LongCat-2.5
- Apodex-1.1-mini vs Ripple-65B Preview
- Arete-27B vs LongCat-2.5
- Arete-27B vs Ripple-65B Preview
- BigBang-v1 vs LongCat-2.5
- BigBang-v1 vs Ripple-65B Preview
- Carbon-X vs LongCat-2.5
- Carbon-X vs Ripple-65B Preview
- Cola2 vs LongCat-2.5
- Cola2 vs Ripple-65B Preview
- Cosmos-Reason2-2B vs LongCat-2.5
- Cosmos-Reason2-2B vs Ripple-65B Preview
- Darwin-36B-Opus vs LongCat-2.5
- Darwin-36B-Opus vs Ripple-65B Preview
- DeepSeek-V3.2 vs LongCat-2.5
- DeepSeek-V3.2 vs Ripple-65B Preview
- DeepSeek V4.1 Flash vs LongCat-2.5
- DeepSeek V4.1 Flash vs Ripple-65B Preview
- DeepSeek-V4-Flash-0731 vs LongCat-2.5
- DeepSeek-V4-Flash-0731 vs Ripple-65B Preview
- Devstral Small 2 vs LongCat-2.5
- Devstral Small 2 vs Ripple-65B Preview
- DiffusionGemma 26B A4B IT vs LongCat-2.5
- DiffusionGemma 26B A4B IT vs Ripple-65B Preview
- EXAONE 4.5 33B vs LongCat-2.5
- EXAONE 4.5 33B vs Ripple-65B Preview
- Gemma 4 12B IT vs LongCat-2.5
- Gemma 4 12B IT vs Ripple-65B Preview
- Gemma 4 26B A4B IT vs LongCat-2.5
- Gemma 4 26B A4B IT vs Ripple-65B Preview
- Gemma 4 31B IT vs LongCat-2.5
- Gemma 4 31B IT vs Ripple-65B Preview
- Gemma 4 E2B IT vs LongCat-2.5
- Gemma 4 E2B IT vs Ripple-65B Preview
- Gemma 4 E4B IT vs LongCat-2.5
- Gemma 4 E4B IT vs Ripple-65B Preview
- GLM-4.5-Air vs LongCat-2.5
- GLM-4.5-Air vs Ripple-65B Preview
- GLM-4.7-Flash vs LongCat-2.5
- GLM-4.7-Flash vs Ripple-65B Preview
- GLM-5.3-Flash vs LongCat-2.5
- GLM-5.3-Flash vs Ripple-65B Preview
- GLM-5.3 vs LongCat-2.5
- GLM-5.3 vs Ripple-65B Preview
- gpt-oss-120b vs LongCat-2.5
- gpt-oss-120b vs Ripple-65B Preview
- gpt-oss-20b vs LongCat-2.5
- gpt-oss-20b vs Ripple-65B Preview
- Granite 4.2 30B vs LongCat-2.5
- Granite 4.2 30B vs Ripple-65B Preview
- Granite 4.2 3B vs LongCat-2.5
- Granite 4.2 3B vs Ripple-65B Preview
- Granite 4.2 8B vs LongCat-2.5
- Granite 4.2 8B vs Ripple-65B Preview
- Hy-Memory-30B-A3B vs LongCat-2.5
- Hy-Memory-30B-A3B vs Ripple-65B Preview
- Hy3 vs LongCat-2.5
- Hy3 vs Ripple-65B Preview
- Inkling-Small vs LongCat-2.5
- Inkling-Small vs Ripple-65B Preview
- Inkling vs LongCat-2.5
- Inkling vs Ripple-65B Preview
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs LongCat-2.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ripple-65B Preview
- Kimi K3.1 Pro vs LongCat-2.5
- Kimi K3.1 Pro vs Ripple-65B Preview
- Kimi K3 vs LongCat-2.5
- Kimi K3 vs Ripple-65B Preview
- Kolibri-1 vs LongCat-2.5
- Kolibri-1 vs Ripple-65B Preview
- Kronos vs LongCat-2.5
- Kronos vs Ripple-65B Preview
- Laguna M.1 vs LongCat-2.5
- Laguna M.1 vs Ripple-65B Preview
- Laguna S 2.1 vs LongCat-2.5
- Laguna S 2.1 vs Ripple-65B Preview
- Laguna XS 2.1 vs LongCat-2.5
- Laguna XS 2.1 vs Ripple-65B Preview
- LBS-27B vs LongCat-2.5
- LBS-27B vs Ripple-65B Preview
- LFM2.5-2.6B vs LongCat-2.5
- LFM2.5-2.6B vs Ripple-65B Preview
- LFM3-1.7B vs LongCat-2.5
- LFM3-1.7B vs Ripple-65B Preview
- LFM3-Audio-2B vs LongCat-2.5
- LFM3-Audio-2B vs Ripple-65B Preview
- LFM3-Omni-2B vs LongCat-2.5
- LFM3-Omni-2B vs Ripple-65B Preview
- LFM3-VL-2B vs LongCat-2.5
- LFM3-VL-2B vs Ripple-65B Preview
- Ling-3.0-tiny vs LongCat-2.5
- Ling-3.0-tiny vs Ripple-65B Preview
- Ling-3.1-flash-1019 vs LongCat-2.5
- Ling-3.1-flash-1019 vs Ripple-65B Preview
- LongCat-2.5 vs MiMo-V2.6 Distill Qwen 9B
- LongCat-2.5 vs MiMo-V2.6-Flash-RL
- LongCat-2.5 vs MiniCPM-o 4.5
- LongCat-2.5 vs MiniCPM-V 4.7 1B
- LongCat-2.5 vs MiniCPM-V 4.7 35B-A3B
- LongCat-2.5 vs MiniCPM5-2B
- LongCat-2.5 vs MiniMax-M2.5
- LongCat-2.5 vs MiniMax-M2.7
- LongCat-2.5 vs MiniMax-M3.1-Flash
- LongCat-2.5 vs Mistral Large 4
- LongCat-2.5 vs Muse Glimmer 30B
- LongCat-2.5 vs Nanbeige4.2-3B
- LongCat-2.5 vs Nanbeige4.3-33B
- LongCat-2.5 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- LongCat-2.5 vs Nemotron 3.5 Lightning 30B A3B
- LongCat-2.5 vs Nemotron 3 Nano 30B A3B
- LongCat-2.5 vs Nemotron 3 Nano 4B
- LongCat-2.5 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- LongCat-2.5 vs Nemotron 3 Super 120B A12B
- LongCat-2.5 vs Nemotron 3 Ultra 550B A55B
- LongCat-2.5 vs North Mini Code 1.0
- LongCat-2.5 vs occamy-1.0
- LongCat-2.5 vs Olmo 3 7B Think
- LongCat-2.5 vs Ornith-1.5-122B
- LongCat-2.5 vs Ornith-1.5-35B-A3B
- LongCat-2.5 vs Ornith-1.5-397B
- LongCat-2.5 vs Ornith-1.5-9B
- LongCat-2.5 vs OTel-2.0-LLM-31B-IT
- LongCat-2.5 vs Qwen-AgentWorld-35B-A3B
- LongCat-2.5 vs Qwen3-30B-A3B-Instruct-2507
- LongCat-2.5 vs Qwen3-4B-Instruct-2507
- LongCat-2.5 vs Qwen3.5-0.8B
- LongCat-2.5 vs Qwen3.5-122B-A10B
- LongCat-2.5 vs Qwen3.5-2B
- LongCat-2.5 vs Qwen3.5-397B-A17B
- LongCat-2.5 vs Qwen3.5-4B
- LongCat-2.5 vs Qwen3.5-9B
- LongCat-2.5 vs Qwen3.6-27B
- LongCat-2.5 vs Qwen3.6-35B-A3B
- LongCat-2.5 vs Qwen3.8-27B
- LongCat-2.5 vs Qwen3.8-Flash-Next
- LongCat-2.5 vs Qwen3-Coder-30B-A3B-Instruct
- LongCat-2.5 vs Qwen3-Coder-Next
- LongCat-2.5 vs Qwen3-Omni-30B-A3B-Instruct
- LongCat-2.5 vs Qwen3-VL-2B-Instruct
- LongCat-2.5 vs Qwen3-VL-30B-A3B-Instruct
- LongCat-2.5 vs Qwen3-VL-32B-Instruct
- LongCat-2.5 vs Qwen3-VL-4B-Instruct
- LongCat-2.5 vs Qwen3-VL-8B-Instruct
- LongCat-2.5 vs Qwopus3.8-27B-Flash-V2
- LongCat-2.5 vs Recursive Flint
- LongCat-2.5 vs SenseNova-Loop-9B-Preview
- LongCat-2.5 vs SmolLM3-3B
- LongCat-2.5 vs Spark-X2.6-4B
- LongCat-2.5 vs Step 3.7 Flash
- LongCat-2.5 vs Swift 1.5 Qwen3.8-27B
- LongCat-2.5 vs Swift 1.5 Qwen3.8-Flash-Next
- LongCat-2.5 vs ThinkingCap (Qwen3.8 27B)
- LongCat-2.5 vs Baidu Unlimited-OCR-2
- LongCat-2.5 vs WeVisOne-VL-2B
- LongCat-2.5 vs WeVisOne-VL-4B
- LongCat-2.5 vs ZAYA1-8B
- MiMo-V2.6 Distill Qwen 9B vs Ripple-65B Preview
- MiMo-V2.6-Flash-RL vs Ripple-65B Preview
- MiniCPM-o 4.5 vs Ripple-65B Preview
- MiniCPM-V 4.7 1B vs Ripple-65B Preview
- MiniCPM-V 4.7 35B-A3B vs Ripple-65B Preview
- MiniCPM5-2B vs Ripple-65B Preview
- MiniMax-M2.5 vs Ripple-65B Preview
- MiniMax-M2.7 vs Ripple-65B Preview
- MiniMax-M3.1-Flash vs Ripple-65B Preview
- Mistral Large 4 vs Ripple-65B Preview
- Muse Glimmer 30B vs Ripple-65B Preview
- Nanbeige4.2-3B vs Ripple-65B Preview
- Nanbeige4.3-33B vs Ripple-65B Preview
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ripple-65B Preview
- Nemotron 3.5 Lightning 30B A3B vs Ripple-65B Preview
- Nemotron 3 Nano 30B A3B vs Ripple-65B Preview
- Nemotron 3 Nano 4B vs Ripple-65B Preview
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Ripple-65B Preview
- Nemotron 3 Super 120B A12B vs Ripple-65B Preview
- Nemotron 3 Ultra 550B A55B vs Ripple-65B Preview
- North Mini Code 1.0 vs Ripple-65B Preview
- occamy-1.0 vs Ripple-65B Preview
- Olmo 3 7B Think vs Ripple-65B Preview
- Ornith-1.5-122B vs Ripple-65B Preview
- Ornith-1.5-35B-A3B vs Ripple-65B Preview
- Ornith-1.5-397B vs Ripple-65B Preview
- Ornith-1.5-9B vs Ripple-65B Preview
- OTel-2.0-LLM-31B-IT vs Ripple-65B Preview
- Qwen-AgentWorld-35B-A3B vs Ripple-65B Preview
- Qwen3-30B-A3B-Instruct-2507 vs Ripple-65B Preview
- Qwen3-4B-Instruct-2507 vs Ripple-65B Preview
- Qwen3.5-0.8B vs Ripple-65B Preview
- Qwen3.5-122B-A10B vs Ripple-65B Preview
- Qwen3.5-2B vs Ripple-65B Preview
- Qwen3.5-397B-A17B vs Ripple-65B Preview
- Qwen3.5-4B vs Ripple-65B Preview
- Qwen3.5-9B vs Ripple-65B Preview
- Qwen3.6-27B vs Ripple-65B Preview
- Qwen3.6-35B-A3B vs Ripple-65B Preview
- Qwen3.8-27B vs Ripple-65B Preview
- Qwen3.8-Flash-Next vs Ripple-65B Preview
- Qwen3-Coder-30B-A3B-Instruct vs Ripple-65B Preview
- Qwen3-Coder-Next vs Ripple-65B Preview
- Qwen3-Omni-30B-A3B-Instruct vs Ripple-65B Preview
- Qwen3-VL-2B-Instruct vs Ripple-65B Preview
- Qwen3-VL-30B-A3B-Instruct vs Ripple-65B Preview
- Qwen3-VL-32B-Instruct vs Ripple-65B Preview
- Qwen3-VL-4B-Instruct vs Ripple-65B Preview
- Qwen3-VL-8B-Instruct vs Ripple-65B Preview
- Qwopus3.8-27B-Flash-V2 vs Ripple-65B Preview
- Recursive Flint vs Ripple-65B Preview
- Ripple-65B Preview vs SenseNova-Loop-9B-Preview
- Ripple-65B Preview vs SmolLM3-3B
- Ripple-65B Preview vs Spark-X2.6-4B
- Ripple-65B Preview vs Step 3.7 Flash
- Ripple-65B Preview vs Swift 1.5 Qwen3.8-27B
- Ripple-65B Preview vs Swift 1.5 Qwen3.8-Flash-Next
- Ripple-65B Preview vs ThinkingCap (Qwen3.8 27B)
- Ripple-65B Preview vs Baidu Unlimited-OCR-2
- Ripple-65B Preview vs WeVisOne-VL-2B
- Ripple-65B Preview vs WeVisOne-VL-4B
- Ripple-65B Preview vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/longcat-2-5-vs-ripple-65b-preview.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/longcat-2-5.json·/api/v1/tools/ripple-65b-preview.json - From a terminal
anchor compare longcat-2-5 ripple-65b-preview(the CLI) - Over MCP
compare_tools {"a": "longcat-2-5", "b": "ripple-65b-preview"}at/mcp, no key