Sign in

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

Kimi K3.1 Pro vs Qwen3.5-397B-A17B

Qwen3.5-397B-A17B scores 64.1 (B) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in 3 of 4 scored categories. Kimi K3.1 Pro leads on documentation and upkeep. 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

Kimi K3.1 ProMoonshot AI · Open-weight model D48.6/100#151 of 160 open-weight models Qwen3.5-397B-A17BAlibaba (Qwen team) · Open-weight model B64.1/100#23 of 160 open-weight models

Which one, for what

Kimi K3.1 Pro D

Best 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

  • Documentation and upkeep, 51 against 34

Watch for

1,561 GB of files, so it needs a node of eight large accelerators at least

Qwen3.5-397B-A17B B

Best for Agents with access to an 8-GPU server, or calling a hosted endpoint, that want the strongest open Qwen3.5 with vision and a plain licence.

Ahead on

  • Reach, 70 against 40
  • Risk, 55 against 50
  • Agent interface, 70 against 65

Watch for

No build fits a 256 GB machine, and Ollama has no local build

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.

Reach Qwen3.5-397B-A17B +30

Kimi K3.1 Pro 40

Memory 0, the only build is Moonshot's 1,561 GB MXFP4 release, far above 256 GB. Runtimes 5, llama.cpp b12242 alone has the model code in a release, since vLLM's recipe needs 0.34.0 and SGLang's cookbook a branch. Builds 10, one precision. Terms 10, free commercial use below a model-as-a-service revenue threshold. Download 10, not gated. Hosted 5, Moonshot's API and Together serve it. 0 + 5 + 10 + 10 + 10 + 5 = 40.

Qwen3.5-397B-A17B 70

Memory scores 0, since even the smallest 4-bit build, LM Studio's MLX 4-bit at 223.9 GB, needs about 269 GB with a fifth added, and Alibaba's own GPTQ-Int4 about 283 GB. Runtimes reach the 25 cap on released llama.cpp, vLLM, SGLang and Transformers and LM Studio's catalogue, though Ollama has no local build. Alibaba's FP8 and GPTQ-Int4 builds give builds 15. Apache 2.0 with nothing added gives terms 15, the ungated repositories give download 10, and Alibaba's Model Studio plus five live providers on Hugging Face give hosted too its 5.

Documentation and upkeep Kimi K3.1 Pro +17

Kimi K3.1 Pro 51

Model card 11, no limitations, languages or cut-off. Training data 5, one general sentence. Last change 20, a commit on 5 November 2026. Responsiveness 0, none of the 8 newest discussions has a reply from Moonshot. Version policy 5, Kimi K3 keeps its repository and no dated note was found. File health 10, the files agree. 11 + 5 + 20 + 0 + 5 + 10 = 51.

Qwen3.5-397B-A17B 34

The card covers five of the seven items and misses limitations and a cut-off (14). Training data is a general description without a cut-off (5). The files last changed on 24 April 2026, 192 days before this check, past the 180-day band and within a year (5), and Qwen's GitHub repository holds only a README and licence, so no reference code of Alibaba's changed later. Alibaba answered none of the 40 most recent questions and reports, recounted on 2 November (0), and GitHub issues couldn't be counted. It's a first release at this size (5), and two template reports and a template fix still wait unanswered (5). 14 + 5 + 5 + 0 + 5 + 5 = 34.

Risk Qwen3.5-397B-A17B +5

Kimi K3.1 Pro 50

File safety 15, safetensors only, less 10 for remote code and prompts built by the repository's script. Provenance 15, Moonshot's own organisation with a hash on every file. Safety evaluation 10, Moonshot's own cyber benchmark results and nobody else's yet. Agent guidance 0, none on the card. Licence risk 10, the revenue threshold. Security programme 0, no way to report a flaw found. 15 + 15 + 10 + 0 + 10 + 0 = 50.

Qwen3.5-397B-A17B 55

Safetensors only with no repository code run on load or to build prompts gives file safety 25, and files in the Qwen organisation the publisher's GitHub links to, each hashed on the Hub, give provenance 15. Plain Apache 2.0 keeps licence risk at 15. Safety evaluation, agent guidance and a security programme score 0. The card has no safety results (its SecCodeBench row is a coding capability), no cautions, and no reporting route was found. The Qwen3.5 blog and Alibaba's security response centre couldn't be read, so both are scored as absent and left open.

Agent interface Qwen3.5-397B-A17B +5

Kimi K3.1 Pro 65

Chat template 10, the format is only code to run. Tool-calling format 10, the parser is named in the runtimes' recipes and the card doesn't say how tools are declared. Trained tool calling 20, several calls a turn on Kimi K3's tools channel. Structured output 5, named among linked guides without the how. Reasoning control 10, reasoning_effort per request. Context 10, 1M tokens. 10 + 10 + 20 + 5 + 10 + 10 = 65.

Qwen3.5-397B-A17B 70

The template ships in the repository (20) and renders several tool calls per turn for a model trained for tool use (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the declaration and call format to the template. Thinking turns off per request and comes back in think tags split by the qwen3 parser (10), and 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model.

Score by category

CategoryWeight this runKimi K3.1 ProQwen3.5-397B-A17BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254070Qwen3.5-397B-A17B +30
Risk20%205055Qwen3.5-397B-A17B +5
Agent interface10%106570Qwen3.5-397B-A17B +5
Documentation and upkeep10%105134Kimi K3.1 Pro +17
Negative events≤1500
TotalD 48.6/100B 64.1/100

Facts side by side

FactKimi K3.1 ProQwen3.5-397B-A17B
KindOpen-weight modelOpen-weight model
VendorMoonshot AIAlibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceKimi K3.1 Pro License (modified MIT)Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-052026-02-16
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (4)

How the scores have moved

Kimi K3.1 Pro

No score change since it was listed.

Qwen3.5-397B-A17B

Verdicts

Kimi K3.1 Pro

Moonshot's newest flagship, eight days old when read, for operators with a rack. Only llama.cpp has its model code in a release, with vLLM and SGLang support still on a release candidate and a branch. The licence is permissive below a revenue threshold, and Moonshot hasn't answered a discussion on the repository yet.

Qwen3.5-397B-A17B

Alibaba's biggest open Qwen3.5, a cousin for hard coding, agent and vision work. Even at 4 bits it needs about 270 GB, so most agents will call it through Alibaba's Model Studio or one of the many providers that host it. The main risk is silence, with no safety results, no agent guidance and template reports without a reply.

Before you call either

Kimi K3.1 Pro

  1. Use Moonshot's API or Together unless you have a node of eight B300-class accelerators
  2. With vLLM use 0.34.0 or later and the recipe's flags, --tool-call-parser kimi_k3 --reasoning-parser kimi_k3
  3. Pass the whole assistant message back in later turns, reasoning_content and tool_calls included, as the card requires
  4. Set reasoning_effort to low, high or max per request. Max is the default and thinking can't be turned off
  5. Kimi K3's model code doesn't load it, because the attention layers changed
  6. Validate JSON output yourself, since the card doesn't document structured output for the weights

Qwen3.5-397B-A17B

  1. The card's server command is vllm serve Qwen/Qwen3.5-397B-A17B --port 8000 --tensor-parallel-size 8 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, and the FP8 build halves the memory
  2. It doesn't fit our 128 GB reference machine at any precision, so call a hosted endpoint instead (Model Studio's Qwen3.5-Plus, or a provider serving Qwen/Qwen3.5-397B-A17B)
  3. On Model Studio pass "enable_thinking": false directly, while vLLM and SGLang take "chat_template_kwargs": {"enable_thinking": false}
  4. Sampling per the card is temperature 0.6, top_p 0.95 and top_k 20 when thinking, and temperature 0.7, top_p 0.8, top_k 20 and presence_penalty 1.5 without
  5. For multi-token prediction in vLLM add --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
  6. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
  7. Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, Kimi K3.1 Pro or Qwen3.5-397B-A17B?

Qwen3.5-397B-A17B scores 64.1 (B) on agent readiness against Kimi K3.1 Pro's 48.6 (D), and leads in 3 of 4 scored categories. Kimi K3.1 Pro leads on documentation and upkeep.

Other comparisons with Kimi K3.1 Pro or Qwen3.5-397B-A17B

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