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

Cola2 vs Kimi K3.1 Pro

Kimi K3.1 Pro scores 48.6 (D) on agent readiness against Cola2's 33.9 (F), and leads in 3 of 4 scored categories. Cola2 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

Which one, for what

Cola2 F

Best for Researchers working on latent or diffusion language models who want a checkpoint to study

Ahead on

  • Documentation and upkeep, 58 against 51

Watch for

No licence stated for the weights

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

  • Reach, 40 against 25
  • Risk, 50 against 40
  • Agent interface, 65 against 20

Watch for

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

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.

Agent interface Kimi K3.1 Pro +45

Cola2 20

Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer. Tool-calling format 0, none. Trained tool calling 0, not trained for tool calling. Structured output 0, Nothing about JSON or schema-constrained output. Reasoning control 0, no reasoning mode. Context 0, no context length is stated. 20 + 0 + 0 + 0 + 0 + 0 = 20.

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.

Reach Kimi K3.1 Pro +15

Cola2 25

Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB. Loaded as BF16, as the card's example does, it needs about half, but the line reads the file size. Runtimes 0, none of the six runs it in a released version. Builds 0, one set of weights and no quantised build. Terms 0, no licence for the weights. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and nothing names an API that serves it. 15 + 0 + 0 + 0 + 10 + 0 = 25.

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.

Risk Kimi K3.1 Pro +10

Cola2 40

File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ByteDance-Seed organisation, which the ByteDance-Seed GitHub repository for the model links to (10). Safety evaluation 0, no safety results. Agent guidance 5, General cautions in the GitHub model card: not instruction-tuned or safety-aligned, not for use as an assistant, for facts or advice, or for high-impact decisions about people. Licence risk 0, With no licence for the weights there is nothing to hold ByteDance to. Security programme 5, the GitHub repository's SECURITY.md sends reports to ByteDance's security centre and says how they're assessed (5). 15 + 15 + 0 + 5 + 0 + 5 = 40.

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.

Documentation and upkeep Cola2 +7

Cola2 58

Model card 8, Intended use and limitations (the out-of-scope list, and the unconverged latent model) and the architecture are on the card and the GitHub model card it links. Training data 15, the GitHub model card names the source (OLMo 2 pretraining text, retokenised) and the mix by stage with token counts, 346.03B in all. Last change 20, All six commits are from 6 November 2026, four days before this check, the last one updating a checksum in the README. Responsiveness 0, no discussions on the repository, so nobody has asked anything yet and the line reads as none answered, as settled in calibration. Version policy 5, A first release. File health 10, Config, files and card agree: F32 weights, a float32 config and a card that says to load them as bfloat16, with SHA256SUMS to check the download. 8 + 15 + 20 + 0 + 5 + 10 = 58.

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.

Score by category

CategoryWeight this runCola2Kimi K3.1 ProEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%252540Kimi K3.1 Pro +15
Risk20%204050Kimi K3.1 Pro +10
Agent interface10%102065Kimi K3.1 Pro +45
Documentation and upkeep10%105851Cola2 +7
Negative events≤1500
TotalF 33.9/100D 48.6/100

Facts side by side

FactCola2Kimi K3.1 Pro
KindOpen-weight modelOpen-weight model
VendorByteDance (Seed)Moonshot AI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceNone stated for the weights (the code is Apache 2.0)Kimi K3.1 Pro License (modified MIT)
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-11-05
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked

Verdicts

Cola2

A research release, and an honest one: ByteDance Seed says it's a base model with an unconverged latent stage, scoring below Llama-3-8B on its own table. It's here for people studying continuous-latent generation. Agents can't use it as a model: 32-token completions, no chat or tools, the repository's own code to load it, and no licence on the weights.

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.

Before you call either

Cola2

  1. Don't plan to use this as your model. It completes short prompts and wasn't tuned to follow instructions
  2. Don't use it commercially on the strength of this listing. The weights have no stated licence
  3. If you study it, read modeling_cola2.py first: trust_remote_code runs it
  4. Pin Transformers below 5, as the card requires
  5. Pass a seeded torch.Generator to generate(). Output varies between runs even with greedy decoding
  6. Check the download with sha256sum -c SHA256SUMS

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

Questions

Which is better for AI agents, Cola2 or Kimi K3.1 Pro?

Kimi K3.1 Pro scores 48.6 (D) on agent readiness against Cola2's 33.9 (F), and leads in 3 of 4 scored categories. Cola2 leads on documentation and upkeep.

Other comparisons with Cola2 or Kimi K3.1 Pro

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.