Sign in

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

Arete-27B vs Inkling

Inkling scores 64.7 (B) on agent readiness against Arete-27B's 55.1 (C), and leads in 3 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 4969 open weights comparisons

Arete-27BNous Research · Open-weight model C55.1/100#105 of 135 open-weight models InklingThinking Machines Lab · Open-weight model B64.7/100#19 of 135 open-weight models

Which one, for what

Arete-27B C

Best for Agents that want Qwen3.8-27B's coding and tool use without its handling of politically sensitive topics, on a 24 GB card or a 128 GB machine

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

Watch for

No quantised build from Nous Research, so the GGUF route depends on a third party

Inkling B

Best for Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.

Ahead on

  • Risk, 70 against 55
  • Agent interface, 85 against 60
  • Documentation and upkeep, 87 against 63

Watch for

The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation

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 Inkling +25

Arete-27B 60

Chat template 20, a Jinja file in the repository. Tool-calling format 10, only the template says it. Trained tool calling 20, several calls a turn and agentic work as an intended use. Structured output 0 and reasoning control 0, neither is documented on the card. Context 10, 262,144 tokens native. 20 + 10 + 20 + 0 + 0 + 10 = 60.

Inkling 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens.

Documentation and upkeep Inkling +24

Arete-27B 63

Model card 8, no limitations, context length, languages or cut-off. Training data 20, the training pairs and the evaluation set are published with their counts. Last change 20, a commit on 6 November 2026. Responsiveness 0, none of 13 discussions has a reply from Nous Research. Version policy 5, a first release. File health 10, the files agree. 8 + 20 + 20 + 0 + 5 + 10 = 63.

Inkling 87

Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page. Training data 15, an EU training-content summary with sources, mix, a July 2026 collection cut-off and filtering. Last change 20, the weights files last changed on 23 July 2026, and Thinking Machines' Inkling renderer in tinker-cookbook changed on 30 October 2026, 3 days ago. Responsiveness 20, Thinking Machines answered 8 of the 12 questions and reports in its discussions. Version policy 5, a first release. File health 10, the files agree and the reports were answered.

Risk Inkling +15

Arete-27B 55

File safety 25, safetensors only and no remote code. Provenance 15, Nous Research's own organisation, linked from its blog, with a hash on every file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 15, plain Apache 2.0. Security programme 0, no way to report a flaw found. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Inkling 70

File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own StrongREJECT and FORTRESS results and commissioned external testers who published nothing. Agent guidance 10, the card says what its refusals miss and which safeguards to add, with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent.

Score by category

CategoryWeight this runArete-27BInklingEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255050even
Risk20%205570Inkling +15
Agent interface10%106085Inkling +25
Documentation and upkeep10%106387Inkling +24
Negative events≤1500
TotalC 55.1/100B 64.7/100

Facts side by side

FactArete-27BInkling
KindOpen-weight modelOpen-weight model
VendorNous ResearchThinking Machines Lab
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-07-23
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

How the scores have moved

Arete-27B

No score change since it was listed.

Inkling

Verdicts

Arete-27B

Qwen3.8-27B with its answers on politically sensitive topics retrained, four days old when read. The training data is published, which is rare. Nous Research ships BF16 only, so a small machine runs it from bartowski's GGUF, and the card documents none of the tool or thinking controls it inherits.

Inkling

Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.

Before you call either

Arete-27B

  1. Start it with llama-server -hf bartowski/NousResearch_Arete-27B-GGUF:Q4_K_M --jinja, a third party's conversion, or serve the BF16 files with vLLM
  2. Use the base's parsers in vLLM, --reasoning-parser qwen3 --tool-call-parser qwen3_coder, and check tool calls first, since the template differs slightly from Qwen3.8-27B's
  3. Thinking switches with enable_thinking in the template. The card's own evaluation ran with it off
  4. Expect answers on politically sensitive topics to differ from Qwen3.8-27B's. That is what the fine-tune is for
  5. Validate JSON output yourself, since structured output isn't documented

Inkling

  1. Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it
  2. On 8 B200 GPUs, SGLang's recipe is sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling
  3. Use the inkling tool parser, not Hermes, and the inkling reasoning parser
  4. Pass reasoning_effort as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh
  5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
  6. Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card
  7. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

Questions

Which is better for AI agents, Arete-27B or Inkling?

Inkling scores 64.7 (B) on agent readiness against Arete-27B's 55.1 (C), and leads in 3 of 4 scored categories.

Other comparisons with Arete-27B or Inkling

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