# InternVL3.5-GPT-OSS-20B-A4B-Preview vs Step 3.7 Flash (slim)

> Step 3.7 Flash scores 59.8 (C) to InternVL3.5-GPT-OSS-20B-A4B-Preview's 53.2 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-step-3-7-flash.md (~10,800 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-step-3-7-flash.json · canonical https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-step-3-7-flash
- 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)

Step 3.7 Flash scores 59.8 (C) on agent readiness against InternVL3.5-GPT-OSS-20B-A4B-Preview's 53.2 (D), and leads in 3 of 4 scored categories. InternVL3.5-GPT-OSS-20B-A4B-Preview leads on risk. 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
- Step 3.7 Flash: C 59.8, rank #93 of 160 open-weight models · https://www.anchorterminal.com/tools/step-3-7-flash.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 Risk, 55 against 45.
- Step 3.7 Flash, good for Teams with a GPU server or a provider account that want an open, long-context agent model with vision Ahead on Reach, 70 against 65; Agent interface, 85 against 45; Documentation and upkeep, 39 against 28.

| Category | InternVL3.5-GPT-OSS-20B-A4B-Preview | Step 3.7 Flash |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 70 |
| Risk (20%) | 55 | 45 |
| Agent interface (10%) | 45 | 85 |
| Documentation and upkeep (10%) | 28 | 39 |

| Fact (where they differ) | InternVL3.5-GPT-OSS-20B-A4B-Preview | Step 3.7 Flash |
| --- | --- | --- |
| Vendor | OpenGVLab (Shanghai AI Laboratory) | StepFun |
| 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 (metadata and card; no LICENSE file) |
| Last release | 2025-09-08 | 2026-06-03 |
| Agent reviews | 1.8/5 (4) | none |

Why the edge:
- Agent interface, Step 3.7 Flash +40: InternVL3.5-GPT-OSS-20B-A4B-Preview 45 (Chat template 20, a Jinja file in the repository, though it doesn't match the tokenizer.); Step 3.7 Flash 85 (Chat template 20, chat_template.jinja in the repository (5,723 characters).)
- Documentation and upkeep, Step 3.7 Flash +11: InternVL3.5-GPT-OSS-20B-A4B-Preview 28 (Model card 8 of 20, the family card misses limitations, context, languages and a cut-off.); Step 3.7 Flash 39 (Model card 14, Intended use, the architecture, the parameters, the context and the language (in the metadata) are on the card.)
- Risk, InternVL3.5-GPT-OSS-20B-A4B-Preview +10: InternVL3.5-GPT-OSS-20B-A4B-Preview 55 (File safety 25, safetensors only and no code in the repository.); Step 3.7 Flash 45 (File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25).)
- Reach, Step 3.7 Flash +5: 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.); Step 3.7 Flash 70 (Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference m…)