# gpt-oss-120b vs Ripple-65B Preview (slim)

> gpt-oss-120b scores 70.2 (BB) to Ripple-65B Preview's 53.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview.md (~7,500 tokens) · this version ~1,330 tokens · JSON https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/gpt-oss-120b-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)

gpt-oss-120b scores 70.2 (BB) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

- gpt-oss-120b: BB 70.2, rank #6 of 121 open-weight models · https://www.anchorterminal.com/tools/gpt-oss-120b.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
- gpt-oss-120b, good for Agents on one 80 GB GPU or a 128 GB unified machine that want an Apache 2.0 reasoning model with wide runtime support Ahead on Reach, 75 against 45; Risk, 95 against 55; Agent interface, 90 against 75. Also Agent-ready, a grade of BB or better.
- 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.

| Category | gpt-oss-120b | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 45 |
| Risk (20%) | 95 | 55 |
| Agent interface (10%) | 90 | 75 |
| Documentation and upkeep (10%) | 45 | 49 |

| Fact (where they differ) | gpt-oss-120b | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | OpenAI | Ricursive Intelligence |
| Last release | 2025-08-26 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Risk, gpt-oss-120b +40: gpt-oss-120b 95 (File safety earns 25, safetensors only, with metal/model.bin a raw format and not pickle, and nothing from the repository runs on load. Provenance earns 15, files in OpenAI's linked organisation with a hash for every file. Safety evaluation earns 20, published results with SecureBio as an outside evaluator. Agent guidance earns 15 for the trained instruction hierarchy with prompt-injection results. Licence risk keeps all 15. The security programme earns 5 for OpenAI's Bugcrowd programme and disclosure policy, and the advisories half scores 0 because GitHub couldn't be checked, not because it was found missing.); 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.)
- Reach, gpt-oss-120b +30: gpt-oss-120b 75 (Memory earns 10, because the smallest 4-bit build, Ollama's 65 GB gpt-oss:120b, needs about 78 GB with the fifth added, which fits the reference machine but not 64 GB. Runtimes earn the full 25 from Transformers, vLLM, SGLang, llama.cpp and Ollama. Builds earn 10, since OpenAI ships one precision, MXFP4. Terms earn 15 for Apache 2.0 with a policy that asks only for lawful use. Download earns 10, with no gate or account. Hosted earns 5, since 11 inference providers serve it on Hugging Face even though OpenAI's own API doesn't.); 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.)
- Agent interface, gpt-oss-120b +15: gpt-oss-120b 90 (The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 25, since OpenAI documents declarations and returned calls in harmony and tells vLLM users to parse with openai-harmony. Trained tool calling earns 10, because each call stops generation, so calls come one at a time. Structured output earns 15 for the documented Response Formats section with a JSON Schema. Reasoning control earns 10, three effort levels per request with the reasoning on the analysis channel. Context earns 10 for 131,072 trained 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.)