Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Apodex-1.1-mini vs Step 3.7 Flash

Apodex-1.1-mini scores 61 (C) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in 2 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Apodex-1.1-miniApodex AI · Open-weight model C61/100#41 of 160 open-weight models Step 3.7 FlashStepFun · Open-weight model C59.8/100#93 of 160 open-weight models

Which one, for what

Apodex-1.1-mini C

Best for Long-running agent tasks with tools on a 32 GB GPU or Mac, or through Apodex's API, under a plain licence

Ahead on

  • Reach, 85 against 70
  • Risk, 65 against 45

Watch for

No safety results, and agent guidance only from the harness

Step 3.7 Flash C

Best for Teams with a GPU server or a provider account that want an open, long-context agent model with vision

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

About 131 GB to run at 4 bits with images, over a 128 GB machine's share

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Risk Apodex-1.1-mini +20

Apodex-1.1-mini 65

File safety 25, safetensors and GGUF only and nothing from the repositories runs. Provenance 15, the files are in the apodex organisation its site links to, with a SHA-256 for every weight file and a SHA256SUMS file for the GGUF. Safety evaluation 0, none published. Agent guidance 5, the recommended harness documents approval gates and a sandbox boundary, but nothing on prompt injection or refusals for the model. Licence risk 15, Apache 2.0 from Qwen3.5-35B-A3B through to this model with no conditions added. Security programme 5, the harness has a disclosure policy with a private address, with no route shown for the weights.

Step 3.7 Flash 45

File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the stepfun-ai organisation, which the card's StepFun platform and model page belong to (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations section and gives no guidance on prompt injection, instruction priority, refusals or safeguards. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and our StepFun API listing found no security.txt, bug bounty or disclosure policy. 15 + 15 + 0 + 0 + 15 + 0 = 45.

Reach Apodex-1.1-mini +15

Apodex-1.1-mini 85

Memory 20, Apodex's Q4_K_M GGUF with its vision projector is 22.6 GB and needs about 27.1 GB with the fifth added, so 32 GB, as do its NVFP4 and GPTQ-Int4 builds. Runtimes 20, the Qwen3.5 MoE architecture runs in released vLLM, SGLang, Transformers and llama.cpp, while Ollama's and LM Studio's entries are the base's, not this model's. Builds 15, Apodex publishes FP8, NVFP4, GPTQ-Int4 and GGUF. Terms 15, Apache 2.0 with nothing added. Download 10, nothing is gated. Hosted 5, Apodex's own API serves it.

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 machine can give a model and within 256 GB. The IQ3 and Q3 builds are below 4 bits and aren't read. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the step3p7 model, and llama.cpp b12242 has the architecture, with StepFun's own GGUF. Four at 5 each, and the card documents all four. Builds 15, StepFun publishes GGUF at five quantised precisions, an FP8 build and an NVFP4 build. Terms 15, Apache 2.0 in the card's metadata and its licence section, an OSI licence with nothing added. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, StepFun's own API serves it, per the card and our StepFun API listing, and Featherless and DeepInfra are live for it on Hugging Face. 5 + 20 + 15 + 15 + 10 + 5 = 70.

Score by category

CategoryWeight this runApodex-1.1-miniStep 3.7 FlashEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258570Apodex-1.1-mini +15
Risk20%206545Apodex-1.1-mini +20
Agent interface10%108585even
Documentation and upkeep10%103839Step 3.7 Flash +1
Negative events≤1500
TotalC 61/100C 59.8/100

Facts side by side

FactApodex-1.1-miniStep 3.7 Flash
KindOpen-weight modelOpen-weight model
VendorApodex AIStepFun
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0 (metadata and card; no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-08-252026-06-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.3/5 (4)none

Verdicts

Apodex-1.1-mini

An agent cousin fine-tuned from Qwen3.5-35B-A3B for long tasks with files, code and tools, with parallel tool calling and about 3B active parameters. It needs 32 GB for Apodex's GGUF, NVFP4 or GPTQ-Int4 builds or about 86 GB in BF16, and Apodex's API serves it too. The main risks are no safety results and no replies from the publisher.

Step 3.7 Flash

A capable open agent model with a clean licence, every kind of build and four released runtimes. Two things hold it back: it's a little too big for a 128 GB machine at 4 bits, whatever the card says, and StepFun has gone quiet on the repository since June. No safety results, limitations or data description.

Before you call either

Apodex-1.1-mini

  1. Serve it with vllm serve apodex/Apodex-1.1-mini --enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3, or the same parsers in SGLang, so tool calls and reasoning come back parsed
  2. For llama.cpp, llama-server -hf apodex/Apodex-1.1-mini-GGUF:Q4_K_M --jinja --reasoning-format deepseek, and the card passes the repository's chat_template.jinja with --chat-template-file
  3. Pass tools through the API's tools parameter rather than in the system prompt, as the card asks
  4. The card recommends temperature 1.0, top_p 0.95, repetition_penalty 1.05 and max_tokens up to 32,768
  5. Send your own system prompt, or set identity_mode, since the template otherwise adds an Apodex identity block
  6. The template keeps all earlier reasoning in the context unless preserve_thinking is false, which grows long agent sessions
  7. Thinking is on by default, send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  8. The card's Python example has a broken line where it runs the tool (available_toolsname), so fix it to available_tools[name](**args) before running
  9. Validate JSON output yourself, since structured output isn't documented

Step 3.7 Flash

  1. On a 128 GB machine the 4-bit GGUF won't fit with a working context. Use StepFun's API or a provider, or a server
  2. On vLLM or SGLang pass --tool-call-parser step3p5 --reasoning-parser step3p5
  3. The card's commands pass trust-remote-code. Released Transformers 5.22.2 has the model built in if you'd rather not run the repository's code
  4. For llama.cpp load the mmproj file from StepFun's GGUF repository for image input
  5. StepFun's API has two hosts. Use the one where your key was issued, api.stepfun.ai or api.stepfun.com
  6. The same model is on our StepFun API listing, with prices and terms

Questions

Which is better for AI agents, Apodex-1.1-mini or Step 3.7 Flash?

Apodex-1.1-mini scores 61 (C) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in 2 of 4 scored categories.

Other comparisons with Apodex-1.1-mini or Step 3.7 Flash

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report