# gpt-oss-120b vs WeVisOne-VL-2B (slim)

> gpt-oss-120b scores 70.2 (BB) to WeVisOne-VL-2B's 61 (C) 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-wevisone-vl-2b.md (~8,950 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/gpt-oss-120b-vs-wevisone-vl-2b.json · canonical https://www.anchorterminal.com/compare/gpt-oss-120b-vs-wevisone-vl-2b
- 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)

gpt-oss-120b scores 70.2 (BB) on agent readiness against WeVisOne-VL-2B's 61 (C), 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 160 open-weight models · https://www.anchorterminal.com/tools/gpt-oss-120b.min.md
- WeVisOne-VL-2B: C 61, rank #83 of 160 open-weight models · https://www.anchorterminal.com/tools/wevisone-vl-2b.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 70; Risk, 95 against 55; Agent interface, 90 against 70. Also Agent-ready, a grade of BB or better.
- WeVisOne-VL-2B, good for Agents that need to locate, count or cut out objects in images on a small GPU, under a permissive licence

| Category | gpt-oss-120b | WeVisOne-VL-2B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 70 |
| Risk (20%) | 95 | 55 |
| Agent interface (10%) | 90 | 70 |
| Documentation and upkeep (10%) | 45 | 48 |

| Fact (where they differ) | gpt-oss-120b | WeVisOne-VL-2B |
| --- | --- | --- |
| Vendor | OpenAI | Tencent (WeChat Vision) |
| Last release | 2025-08-26 | 2026-10-28 |
| 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.); WeVisOne-VL-2B 55 (File safety 15, the backbone is safetensors, but mask_decoder.pt, a PyTorch pickle the card calls a required component, sits beside it.)
- Agent interface, gpt-oss-120b +20: gpt-oss-120b 90 (The chat template earns 20, a Jinja file in the repository.); WeVisOne-VL-2B 70 (Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template.)
- Reach, gpt-oss-120b +5: 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…); WeVisOne-VL-2B 70 (Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 4.92 GB, and 4.92 GB × 1.2 = 5.9 GB, within 16 GB.)