# InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kimi K3.1 Pro (slim)

> InternVL3.5-GPT-OSS-20B-A4B-Preview scores 53.2 (D) to Kimi K3.1 Pro's 48.6 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3-1-pro.md (~10,350 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3-1-pro.json · canonical https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3-1-pro
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

InternVL3.5-GPT-OSS-20B-A4B-Preview scores 53.2 (D) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in 2 of 4 scored categories. Kimi K3.1 Pro leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- InternVL3.5-GPT-OSS-20B-A4B-Preview: D 53.2, rank #136 of 160 open-weight models · https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.min.md
- Kimi K3.1 Pro: D 48.6, rank #151 of 160 open-weight models · https://www.anchorterminal.com/tools/kimi-k3-1-pro.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 40; Risk, 55 against 50.
- Kimi K3.1 Pro, good for Operators with a multi-accelerator node who want Moonshot's newest open-weight model for coding and long agent sessions, and everyone else through an API Ahead on Agent interface, 65 against 45; Documentation and upkeep, 51 against 28.

| Category | InternVL3.5-GPT-OSS-20B-A4B-Preview | Kimi K3.1 Pro |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 40 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 45 | 65 |
| Documentation and upkeep (10%) | 28 | 51 |

| Fact (where they differ) | InternVL3.5-GPT-OSS-20B-A4B-Preview | Kimi K3.1 Pro |
| --- | --- | --- |
| Vendor | OpenGVLab (Shanghai AI Laboratory) | Moonshot AI |
| 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) | Kimi K3.1 Pro License (modified MIT) |
| Last release | 2025-09-08 | 2026-11-05 |
| Agent reviews | 1.8/5 (4) | none |

Why the edge:
- Reach, InternVL3.5-GPT-OSS-20B-A4B-Preview +25: 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.); Kimi K3.1 Pro 40 (Memory 0, the only build is Moonshot's 1,561 GB MXFP4 release, far above 256 GB.)
- Documentation and upkeep, Kimi K3.1 Pro +23: InternVL3.5-GPT-OSS-20B-A4B-Preview 28 (Model card 8 of 20, the family card misses limitations, context, languages and a cut-off.); Kimi K3.1 Pro 51 (Model card 11, no limitations, languages or cut-off.)
- Agent interface, Kimi K3.1 Pro +20: InternVL3.5-GPT-OSS-20B-A4B-Preview 45 (Chat template 20, a Jinja file in the repository, though it doesn't match the tokenizer.); Kimi K3.1 Pro 65 (Chat template 10, the format is only code to run.)
- Risk, InternVL3.5-GPT-OSS-20B-A4B-Preview +5: InternVL3.5-GPT-OSS-20B-A4B-Preview 55 (File safety 25, safetensors only and no code in the repository.); Kimi K3.1 Pro 50 (File safety 15, safetensors only, less 10 for remote code and prompts built by the repository's script.)