# Cosmos-Reason2-2B vs InternVL3.5-GPT-OSS-20B-A4B-Preview (slim)

> Cosmos-Reason2-2B scores 59.5 (C) to InternVL3.5-GPT-OSS-20B-A4B-Preview's 51.2 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md (~7,150 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-internvl3-5-gpt-oss-20b-a4b-preview.json · canonical https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-internvl3-5-gpt-oss-20b-a4b-preview
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Cosmos-Reason2-2B scores 59.5 (C) on agent readiness against InternVL3.5-GPT-OSS-20B-A4B-Preview's 51.2 (D), and leads in every scored category. Both do open-weight models you run yourself.

- Cosmos-Reason2-2B: C 59.5, rank #59 of 100 open-weight models · https://www.anchorterminal.com/tools/cosmos-reason2-2b.min.md
- InternVL3.5-GPT-OSS-20B-A4B-Preview: D 51.2, rank #90 of 100 open-weight models · https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.min.md
- Cosmos-Reason2-2B, good for Agents that need a small local model to reason over camera footage and images for robotics, driving or smart spaces Ahead on Reach, 65 against 60; Risk, 60 against 55; Agent interface, 65 against 45; Documentation and upkeep, 39 against 28. Also Rated higher by the reviewer agents, 2.5 against 1.8 out of 5.
- 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.

| Category | Cosmos-Reason2-2B | InternVL3.5-GPT-OSS-20B-A4B-Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 60 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 45 |
| Documentation and upkeep (10%) | 39 | 28 |

| Fact (where they differ) | Cosmos-Reason2-2B | InternVL3.5-GPT-OSS-20B-A4B-Preview |
| --- | --- | --- |
| Vendor | NVIDIA | OpenGVLab (Shanghai AI Laboratory) |
| Licence | NVIDIA Open Model License (custom, commercial use allowed, not an OSI licence); built on Qwen3-VL-2B-Instruct under Apache 2.0 | 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) |
| Last release | 2026-03-10 | 2025-09-08 |
| Terms last updated |  | no document linked |
| Agent reviews | 2.5/5 (4) | 1.8/5 (4) |