# InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ripple-65B Preview (slim)

> Ripple-65B Preview and InternVL3.5-GPT-OSS-20B-A4B-Preview score within a point of each other for open-weight models you run yourself, 53.3 and 53.2 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview.md (~8,650 tokens) · this version ~1,380 tokens · JSON https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-04
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Ripple-65B Preview and InternVL3.5-GPT-OSS-20B-A4B-Preview score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). InternVL3.5-GPT-OSS-20B-A4B-Preview leads on reach. Both do open-weight models you run yourself.

- InternVL3.5-GPT-OSS-20B-A4B-Preview: D 53.2, rank #104 of 121 open-weight models · https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.min.md
- Ripple-65B Preview: D 53.3, rank #103 of 121 open-weight models · https://www.anchorterminal.com/tools/ripple-65b-preview.min.md
- InternVL3.5-GPT-OSS-20B-A4B-Preview, good for Agents with 64 GB to spare that want an Apache-licensed image and video reader with optional thinking and can live with a stale preview. Ahead on Reach, 65 against 45.
- Ripple-65B Preview, good 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 Agent interface, 75 against 45; Documentation and upkeep, 49 against 28.

| Category | InternVL3.5-GPT-OSS-20B-A4B-Preview | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 45 | 75 |
| Documentation and upkeep (10%) | 28 | 49 |

| Fact (where they differ) | InternVL3.5-GPT-OSS-20B-A4B-Preview | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | OpenGVLab (Shanghai AI Laboratory) | Ricursive Intelligence |
| Licence | Apache-2.0; a merge of openai/gpt-oss-20b (Apache 2.0 with OpenAI's usage policy) and OpenGVLab/InternViT-300M-448px-V2_5 (MIT) | Apache-2.0 |
| Last release | 2025-09-08 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 1.8/5 (4) | none |

Why the edge:
- Agent interface, Ripple-65B Preview +30: InternVL3.5-GPT-OSS-20B-A4B-Preview 45 (Chat template 20, a Jinja file in the repository, though it doesn't match the tokenizer. Tool-calling format 10 of 25, only the twin's inherited harmony template mentions tools. Trained tool calling 0, no evidence it was trained to call tools. Structured output 0. Reasoning control 10, a system prompt turns thinking on and the card says the reasoning comes back in think tags. Context 5, trained at 32K tokens.); Ripple-65B Preview 75 (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, Ripple-65B Preview +21: InternVL3.5-GPT-OSS-20B-A4B-Preview 28 (Model card 8 of 20, the family card misses limitations, context, languages and a cut-off. Training data 5, described without a cut-off. Last change 0, the last commit to either repository is 8 September 2025 and to OpenGVLab's reference code 22 September 2025, over a year before 4 November 2026. Responsiveness 10, OpenGVLab answered 3 of 8 questions across the two repositories, none since September 2025. Version policy 5, a first release. File health 0, the template uses markers the tokenizer doesn't have and contradicts the twin's template, and the card names the wrong language model in its licence line.); Ripple-65B Preview 49 (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.)
- Reach, InternVL3.5-GPT-OSS-20B-A4B-Preview +20: InternVL3.5-GPT-OSS-20B-A4B-Preview 65 (Memory 15 of 30, the only builds are BF16 at 42.5 GB by the repository's safetensors index, or 51 GB with a fifth added, which fits 64 GB. Runtimes 25, Transformers and vLLM load this repository, and SGLang, llama.cpp and Ollama (through llama.cpp b11963, which Ollama v0.40.14 pins) run the same weights in their GitHub format. Builds 0, OpenGVLab publishes no quantised build. Terms 15, Apache 2.0 with nothing added by the bases. Download 10, not gated. Hosted 0, no provider serves it.); 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.)