# Ripple-65B Preview > Ricursive Intelligence's 65B dense model, pretrained from scratch and post-trained for agentic coding, on Hugging Face in BF16 and NVFP4 under Apache 2.0. Its custom architecture needs Ricursive's own model code to run. - Canonical: https://www.anchorterminal.com/tools/ripple-65b-preview - Pricing: https://www.anchorterminal.com/tools/ripple-65b-preview#pricing - Reviews: https://www.anchorterminal.com/tools/ripple-65b-preview#reviews - Markdown: https://www.anchorterminal.com/tools/ripple-65b-preview.md (~9,000 tokens) - Slim: https://www.anchorterminal.com/tools/ripple-65b-preview.min.md (~1,880 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/ripple-65b-preview.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT ripple-65b-preview.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-04 ## Overview **Grade D · 53.3/100 · rank #103 of 121 open-weight models · #78 in Open-weight models · not agent-ready · confidence low** ## Assessment 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. ## Facts | Field | Value | | --- | --- | | Vendor | Ricursive Intelligence (https://www.ricursive.com/ripple) | | Kind | Open-weight model | | Category | Open-weight models (https://www.anchorterminal.com/categories/open-weights) | | Auth | None · The weights download from Hugging Face with no account, token or terms to accept. Neither the BF16 nor the NVFP4 repository is gated (checked 2026-11-04). | | Pricing | Free (Free) · Free to download and use, commercial use included, under Apache 2.0. Running it yourself costs the hardware, 129.6 GB for the BF16 files and 57.2 GB for the NVFP4 build by the Hub's file pages. Ricursive's launch post names Together AI, GMI Cloud and OpenRouter as hosts, but Together's model page says coming soon (checked 2026-11-04). | | x402 | No · Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-04). | | Licence | Apache-2.0 | | Packages | huggingface: `ricursiveAI/Ripple-65B-Preview`; huggingface: `ricursiveAI/Ripple-65B-Preview-NVFP4` | | Source | https://huggingface.co/ricursiveAI/Ripple-65B-Preview | | Docs | https://huggingface.co/ricursiveAI/Ripple-65B-Preview | | llms.txt | not found | | Last release | 2026-11-04 | | Surface graded | The open weights at huggingface.co/ricursiveAI/Ripple-65B-Preview and its NVFP4 build, read from the model cards, the Hub's model info and file pages, config.json, tokenizer_config.json, the licence, the server README and the Spark loader on 4 November 2026. Nothing was downloaded or run. Hosted copies aren't graded | | Model | RicursiveForCausalLM, 64,782,689,360 BF16 parameters per the Hub. Dense, 80 layers, hidden size 5,120, 80 attention heads and 8 KV heads, sliding window 1,024 on four layers of every five, vocabulary 100,352. Text in, text out. Pretrained from scratch, not built on another model, starting from Olmo 3's model ladder | | Builds | BF16 instruct (16 safetensors shards, 129.6 GB), NVFP4 instruct (6 shards, 57.2 GB, NVFP4 MLPs and BF16 attention, which its card calls experimental and conservative), a BF16 pretrain-only base model and a DFlash2 draft model for speculative decoding, each in its own repository. No GGUF or other build from Ricursive | | Files | Safetensors with a SHA-256 for every LFS file on the Hub, chat_template.jinja, tokenizer files, configuration_ricursive.py and modeling_ricursive.py (loaded through auto_map), and inference folders of Python (serve.py, model.py, ripple_format.py, and spark.py with a notebook in the NVFP4 repository). No pickle files | | Runtimes | Ricursive's server registers its own model.py and parsers into SGLang 0.5.19 on two B200 GPUs, and its Spark loader does the same for the NVFP4 build. Transformers loads it only through trust_remote_code. No released llama.cpp, Ollama, vLLM, SGLang, LM Studio or Transformers version was found to run the ricursive architecture with its own code | | Context | Up to 1M tokens per the card, after long-context stages at 2M-token sequences. config.json allows 2,097,152 positions, tokenizer_config.json says 131,072, and the server defaults to 16K | | Tools and reasoning | The tools-aware ChatML template takes tools in tools tags and renders one or more tool_call blocks per turn. With Ricursive's ripple parsers the server returns reasoning_content, content and tool_calls separately. The template has no thinking switch and no reasoning-effort levels | | Hardware | The server README targets two B200 GPUs at TP2 with a 16K context. The cards say the model fits an NVIDIA DGX Spark with the NVFP4 build, and give 250 tokens a second on 2 × B200 at batch 8 in BF16 | | Training data | 12T tokens of text-only, predominantly English and code, then 200B midtraining, 6.5B long-context, 183B SFT and 13.5B long-context SFT tokens and RL, per the card's stage table. No sources, filtering or knowledge cut-off | | Ricursive's figures | Vendor-reported at full BF16 and maximum effort. Terminal-Bench 2.1 80.5, SWE-bench Verified 76.5, SWE-bench Pro v1.0 61.42, DeepSWE 1.1 44.3, MCP Atlas 71.67, GPQA Diamond 85.2, MMLU-Pro 84.2, IFBench 79.2, AA-LCR 75.0. Safety FORTRESS adversarial 83.8, FORTRESS benign 95.5, StrongREJECT 97.5. Harnesses are OpenCode or Terminus 2 | | Capabilities | model.open-weights | | Tags | open-weights, model, dense, reasoning, tool-calling, coding, apache-2.0, safetensors, remote-code, self-hosted, new | | JSON | https://www.anchorterminal.com/api/v1/tools/ripple-65b-preview.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-04 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: low. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Capability | 35% | pending | pending | n/a | | Reach | 25% | 38.5 | 45 | 17.3 | | Risk | 20% | 30.8 | 55 | 16.9 | | Agent interface | 10% | 15.4 | 75 | 11.5 | | Documentation and upkeep | 10% | 15.4 | 49 | 7.5 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **53.3 → D** | ### Why each score - Capability: Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start. - Reach 45 (checked 2026-11-04): 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 55 (checked 2026-11-04): 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. - Agent interface 75 (checked 2026-11-04): Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M. - Documentation and upkeep 49 (checked 2026-11-04): Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M. Fix list, everything this grade says the listing lacks, the biggest gain first (15 items). What it covers is at https://www.anchorterminal.com/fixes/ripple-65b-preview.md (JSON https://www.anchorterminal.com/fixes/ripple-65b-preview.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "ripple-65b-preview", "plan": "read"}`, free while the beta runs ### What we couldn't check - Capability is pending. Ricursive's 80.52 on Terminal-Bench 2.1 and the "U.S. open-weight SOTA" and "surpassing" claims are its own and couldn't be checked against an independent result, so no deduction. Re-check the Terminal-Bench 2.1 leaderboard, Vals AI and Epoch AI in a week - Hosted is 0. Together says coming soon, GMI Cloud's console couldn't be read under robots.txt, and OpenRouter isn't requested. If two providers serve it, hosted is 5 - Runtimes is 0 on release day. If SGLang, vLLM or Transformers ship ricursive support in a release, each is 5 and the remote-code 10 off file safety may lift - Tool-calling format is read at 25 because Ricursive documents the format and names its parser in SGLang 0.5.19. Read as the template-only 10 the interface score is 60 and the total about 51.0 - The base model repository was created on 14 October 2026, before release; the instruct repositories on 4 November - www.ricursive.com is a Framer site, and Framer's own Acceptable Use Policy bars automated access to content it hosts (framer re-check, 4 November). The framer reading paused framer.com hosts only; whether it reaches customers' sites on Framer is for the founder ### Sources - launch post, Terminal-Bench 2.1 claim, cost, architecture, hosts: (seen 2026-11-04) - home page, company name, links: (seen 2026-11-04) - legal pages, rendered by script and unreadable: (seen 2026-11-04) - security.txt, 404: (seen 2026-11-04) - model card, benchmark tables, stage table, safety figures: (seen 2026-11-04) - Hub model info, gating, likes, parameters, created date, file list, providers (none): (seen 2026-11-04) - file page, sizes, SHA-256 and last commits: (seen 2026-11-04) - config.json: (seen 2026-11-04) - tokenizer_config.json: (seen 2026-11-04) - LICENSE, Apache 2.0: (seen 2026-11-04) - server README, SGLang 0.5.19, parsers, tool calling: (seen 2026-11-04) - discussions, none: (seen 2026-11-04) - NVFP4 card: (seen 2026-11-04) - NVFP4 Hub model info: (seen 2026-11-04) - NVFP4 file page, sizes and the in-place replacement commit: (seen 2026-11-04) - NVFP4 config.json, quantisation groups: (seen 2026-11-04) - Spark loader, SGLang plugin registration: (seen 2026-11-04) - base model Hub info, created 14 October 2026: (seen 2026-11-04) - Hugging Face organisation page: (seen 2026-11-04) - Together AI model page, coming soon: (seen 2026-11-04) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/ripple-65b-preview/history.json - 2026-11-04: graded 53.3 D (methodology 0.7) ## Who's behind it (provenance 36/100, checked 2026-11-04) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Ricursive Intelligence, Inc. | 20/20 | | Domain age | ricursive.com, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | published, not read by us yet | 4/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | | People named | not researched yet | n/a | | Support route | help pages, a community | 5/5 | Every page on www.ricursive.com ends with "© 2026 Ricursive Intelligence, Inc.". The site links the Hugging Face organisation ricursiveAI (fullname Ricursive Intelligence), which publishes the four Ripple repositories. RDAP wasn't queried, by the run's rules. The Apache 2.0 LICENSE in the repository governs the weights and stands in for terms of service. The site's own legal pages (/legal and /legal/terms, titled Model Attribution Terms) render their text by script only and couldn't be read. Nothing is hosted by Ricursive, so no privacy policy or status page is scored. No changelog. The repositories' commit messages are uploads and one in-place swap of the NVFP4 checkpoint on release day. www.ricursive.com/.well-known/security.txt is 404 on 4 November 2026, and the only contact on the card and site is a general one. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://huggingface.co/ricursiveAI/Ripple-65B-Preview/blob/main/LICENSE), not read yet. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Humans behind the project (researched 2026-11-04 from public pages, not part of the grade) ### Key people - No people named yet. - Note: No person is named with a role on a page we could read. www.ricursive.com names no one; its home page links a TIME100 AI 2026 entry whose address names Azalia Mirhoseini and Anna Goldie, but time.com answered 406 and the entry wasn't read, so their roles aren't given here. The model card is authored by "Ricursive Intelligence" only, and the Hugging Face organisation keeps its member list private. TechCrunch, linked from the home page about the company's funding, disallows ClaudeBot in robots.txt and wasn't read; The New York Times and The Wall Street Journal articles it links are paywalled. Roster empty pending a first-hand page. No LinkedIn or X was read. ### Getting support - Help: https://huggingface.co/ricursiveAI/Ripple-65B-Preview/discussions - Community (Hugging Face discussions): https://huggingface.co/ricursiveAI/Ripple-65B-Preview/discussions - Sources: https://www.ricursive.com/, https://www.ricursive.com/ripple, https://huggingface.co/ricursiveAI, https://huggingface.co/ricursiveAI/Ripple-65B-Preview ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. No hosted version of these weights has a price on OpenRouter, so what a task costs is your own hardware and power. ## Strengths - Apache 2.0 with nothing added, ungated, from the organisation Ricursive's site links to - A tools-aware chat template with several calls a turn, and a server that returns reasoning, content and tool calls separately - Trained for long context at 2M-token sequences, with 1M stated - Base model and a speculative-decoding draft published beside the instruct model - Safetensors only, with a checksum on every file ## Weaknesses - No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code - The smallest build is 57.2 GB NVFP4, for NVIDIA Blackwell only, and there is no GGUF - No independent benchmark yet, and the top-ranking claim rests on Ricursive's own Terminal-Bench 2.1 run - Thinking can't be turned off or budgeted - No safety guidance for agent use, no security contact and no knowledge cut-off ## Before you call it (notes for agents) 1. Run Ricursive's launcher from inference/server with `uv run --script serve.py` on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default 2. The launcher turns on `--reasoning-parser ripple` and `--tool-call-parser ripple`; without them tool calls come back as raw text inside tool_call tags 3. For `tool_choice: "required"` set `strict: true` and `additionalProperties: false` on each function, which the README says stopped extra argument fields 4. Leave room in `max_tokens` for reasoning as well as the answer, since thinking is always on 5. Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support ## Get started Install: ```bash hf download ricursiveAI/Ripple-65B-Preview --local-dir ./ripple-65b hf download ricursiveAI/Ripple-65B-Preview-DFlash2 --local-dir ./ripple-dflash2 cd ripple-65b/inference/server CUDA_VISIBLE_DEVICES=0,1 uv run --script serve.py \ --model-path ../.. \ --speculative-draft-model-path ../../../ripple-dflash2 ``` First request: ```bash curl http://127.0.0.1:30000/v1/chat/completions \ -H 'Content-Type: application/json' \ -d '{"model": "ripple", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 128}' ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Qwen3-Embedding-8B | BB | 75.4 | open-weight #1 | model.open-weights | no | https://www.anchorterminal.com/tools/qwen3-embedding-8b.md | | Gemma 4 31B IT | BB | 74.1 | open-weight #2 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-31b-it.md | | Qwen3-Embedding-4B | BB | 73.6 | open-weight #3 | model.open-weights | no | https://www.anchorterminal.com/tools/qwen3-embedding-4b.md | | Gemma 4 12B IT | BB | 72.3 | open-weight #4 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-12b-it.md | | Gemma 4 26B A4B IT | BB | 72.2 | open-weight #5 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.md | | gpt-oss-120b | BB | 70.2 | open-weight #6 | model.open-weights | no | https://www.anchorterminal.com/tools/gpt-oss-120b.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Ricursive says Ripple-65B Preview sets a U.S. open-weight state of the art on agentic coding, 80.52 on Terminal-Bench 2.1, above Reflection Beam 501B (80.1), Muse Spark Open 816B (76.4), Inkling 975B (63.8) and Nemotron 3 Ultra 550B (56.4). These are Ricursive's own runs set beside the other labs' self-reported numbers, not our measurement, and no independent result for Ripple was found on 4 November 2026 (source: ) - On Ricursive's own table Reflection Beam is ahead of Ripple on SWE-bench Verified (81.6 against 76.5), SWE-bench Pro v1.0 (66.1 against 61.42) and GPQA Diamond, and Muse Spark Open on DeepSWE 1.1, MCP Atlas and SciCode, so the top-ranking claim rests on Terminal-Bench 2.1 alone. Ricursive notes its italic figures for other models are its own in-house runs (source: ) - Ricursive says it trained the model for a full R&D cost of $32M, from an Olmo 3 model ladder, with a team that grew from one to five people. Ricursive's claim (source: ) - The architecture is Ricursive's own (RicursiveForCausalLM, model_type ricursive), 80 layers with four sliding-window layers of 1,024 tokens to each global one, gated attention and value residuals. It loads through the repository's Python files or Ricursive's SGLang plugin, not a runtime's own code (source: ) - 88 likes on the BF16 repository and 14 on the NVFP4 one on 4 November 2026, the day of release, with no downloads counted yet and no discussions (source: ) - #78 of 86 in Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md - All 3674 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md ## Compare - [Agents-A1-4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/agents-a1-4b-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Apertus v1.5 8B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Apodex-1.1-mini vs Ripple-65B Preview](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [BigBang-v1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/bigbang-v1-vs-ripple-65b-preview.md): C 56.3 vs D 53.3 - [Carbon-X vs Ripple-65B Preview](https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Cosmos-Reason2-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-ripple-65b-preview.md): C 59.5 vs D 53.3 - [Darwin-36B-Opus vs Ripple-65B Preview](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [DeepSeek-V3.2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ripple-65b-preview.md): C 58.6 vs D 53.3 - [DeepSeek V4.1 Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-ripple-65b-preview.md): C 61.5 vs D 53.3 - [DeepSeek-V4-Flash-0731 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-ripple-65b-preview.md): C 61.9 vs D 53.3 - [DiffusionGemma 26B A4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview.md): D 51.3 vs D 53.3 - [Gemma 4 12B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ripple-65b-preview.md): BB 72.3 vs D 53.3 - [Gemma 4 26B A4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-ripple-65b-preview.md): BB 72.2 vs D 53.3 - [Gemma 4 31B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-ripple-65b-preview.md): BB 74.1 vs D 53.3 - [Gemma 4 E2B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-ripple-65b-preview.md): C 60.4 vs D 53.3 - [Gemma 4 E4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-ripple-65b-preview.md): B 63.2 vs D 53.3 - [GLM-4.5-Air vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-4-5-air-vs-ripple-65b-preview.md): C 60.3 vs D 53.3 - [GLM-4.7-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-ripple-65b-preview.md): B 63 vs D 53.3 - [GLM-5.3-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview.md): B 65.1 vs D 53.3 - [GLM-5.3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview.md): B 64.6 vs D 53.3 - [gpt-oss-120b vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview.md): BB 70.2 vs D 53.3 - [gpt-oss-20b vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview.md): B 69.9 vs D 53.3 - [Granite 4.2 3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ripple-65b-preview.md): C 59.8 vs D 53.3 - [Hy3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview.md): B 62.6 vs D 53.3 - [Inkling-Small vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-small-vs-ripple-65b-preview.md): B 67 vs D 53.3 - [Inkling vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview.md): B 64.7 vs D 53.3 - [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ripple-65B Preview](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview.md): D 53.2 vs D 53.3 - [Kimi K3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview.md): B 62.4 vs D 53.3 - [Kolibri-1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kolibri-1-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Kronos vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kronos-vs-ripple-65b-preview.md): C 55.2 vs D 53.3 - [Laguna M.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-m-1-vs-ripple-65b-preview.md): C 56.7 vs D 53.3 - [Laguna S 2.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Laguna XS 2.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [LBS-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lbs-27b-vs-ripple-65b-preview.md): C 55.8 vs D 53.3 - [LFM2.5-2.6B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-ripple-65b-preview.md): D 50.3 vs D 53.3 - [Ling-3.0-tiny vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-ripple-65b-preview.md): C 56.2 vs D 53.3 - [MiMo-V2.6 Distill Qwen 9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [MiniCPM-o 4.5 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [MiniCPM5-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minicpm5-2b-vs-ripple-65b-preview.md): C 59.7 vs D 53.3 - [MiniMax-M2.5 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m2-5-vs-ripple-65b-preview.md): C 59 vs D 53.3 - [MiniMax-M2.7 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m2-7-vs-ripple-65b-preview.md): C 57.6 vs D 53.3 - [MiniMax-M3.1-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-ripple-65b-preview.md): C 54.3 vs D 53.3 - [Mistral Large 4 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/mistral-large-4-vs-ripple-65b-preview.md): C 54.6 vs D 53.3 - [Muse Glimmer 30B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-ripple-65b-preview.md): BB 70 vs D 53.3 - [Nanbeige4.3-33B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ripple-65b-preview.md): C 60.8 vs D 53.3 - [NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Nemotron 3.5 Lightning 30B A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-ripple-65b-preview.md): B 64.7 vs D 53.3 - [Nemotron 3 Nano 30B A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-ripple-65b-preview.md): B 67.6 vs D 53.3 - [Nemotron 3 Nano 4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-ripple-65b-preview.md): C 56.8 vs D 53.3 - [Nemotron 3 Nano Omni 30B A3B Reasoning vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-ripple-65b-preview.md): C 61.2 vs D 53.3 - [Nemotron 3 Super 120B A12B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-ripple-65b-preview.md): B 66.7 vs D 53.3 - [Nemotron 3 Ultra 550B A55B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-ripple-65b-preview.md): B 69.3 vs D 53.3 - [occamy-1.0 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/occamy-1-0-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Olmo 3 7B Think vs Ripple-65B Preview](https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview.md): D 52.3 vs D 53.3 - [Ornith-1.5-35B-A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Ornith-1.5-397B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-ripple-65b-preview.md): C 59 vs D 53.3 - [Ornith-1.5-9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Qwen3-30B-A3B-Instruct-2507 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-ripple-65b-preview.md): C 56.6 vs D 53.3 - [Qwen3-4B-Instruct-2507 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-ripple-65b-preview.md): C 54.5 vs D 53.3 - [Qwen3.5-0.8B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-ripple-65b-preview.md): D 46.7 vs D 53.3 - [Qwen3.5-122B-A10B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-ripple-65b-preview.md): B 63.1 vs D 53.3 - [Qwen3.5-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview.md): D 50.5 vs D 53.3 - [Qwen3.5-397B-A17B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-ripple-65b-preview.md): B 64.1 vs D 53.3 - [Qwen3.5-4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-4b-vs-ripple-65b-preview.md): C 61.2 vs D 53.3 - [Qwen3.5-9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-9b-vs-ripple-65b-preview.md): C 60.5 vs D 53.3 - [Qwen3.6-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-6-27b-vs-ripple-65b-preview.md): B 66.7 vs D 53.3 - [Qwen3.6-35B-A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-ripple-65b-preview.md): B 62.7 vs D 53.3 - [Qwen3.8-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-8-27b-vs-ripple-65b-preview.md): B 68.6 vs D 53.3 - [Qwen3.8-Flash-Next vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-ripple-65b-preview.md): C 61.8 vs D 53.3 - [Qwen3-Coder-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-ripple-65b-preview.md): C 55.7 vs D 53.3 - [Qwen3-Coder-Next vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-coder-next-vs-ripple-65b-preview.md): C 57.6 vs D 53.3 - [Qwen3-Omni-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-ripple-65b-preview.md): E 41.8 vs D 53.3 - [Qwen3-VL-2B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Qwen3-VL-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-ripple-65b-preview.md): C 58 vs D 53.3 - [Qwen3-VL-32B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-ripple-65b-preview.md): C 56.4 vs D 53.3 - [Qwen3-VL-4B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-ripple-65b-preview.md): D 52.6 vs D 53.3 - [Qwen3-VL-8B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-ripple-65b-preview.md): C 54.9 vs D 53.3 - [Qwopus3.8-27B-Flash-V2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Recursive Flint vs Ripple-65B Preview](https://www.anchorterminal.com/compare/recursive-flint-vs-ripple-65b-preview.md): C 61 vs D 53.3 - [Ripple-65B Preview vs SmolLM3-3B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-smollm3-3b.md): D 53.3 vs C 61 - [Ripple-65B Preview vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-spark-x2-6-4b.md): D 53.3 vs C 61 - [Ripple-65B Preview vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-27b.md): D 53.3 vs C 61 - [Ripple-65B Preview vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-flash-next.md): D 53.3 vs C 54.2 - [Ripple-65B Preview vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-thinkingcap-qwen3-8-27b.md): D 53.3 vs C 61 - [Ripple-65B Preview vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-unlimited-ocr-2.md): D 53.3 vs C 54.2 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on ricursive.com or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "ripple-65b-preview", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Ripple-65B Preview on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Ripple-65B Preview on Anchor Terminal](https://www.anchorterminal.com/badges/ripple-65b-preview.svg)](https://www.anchorterminal.com/tools/ripple-65b-preview) ``` Plain link: ```html Ripple-65B Preview on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Ripple-65B Preview is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/ripple-65b-preview-dark.png - Light: https://www.anchorterminal.com/assets/share/ripple-65b-preview-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp