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

Arete-27B vs Darwin-36B-Opus

Darwin-36B-Opus scores 61 (C) on agent readiness against Arete-27B's 55.1 (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 4969 open weights comparisons

Arete-27BNous Research · Open-weight model C55.1/100#105 of 135 open-weight models Darwin-36B-OpusFINAL-Bench (VIDRAFT) · Open-weight model C61/100#43 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

Darwin-36B-Opus C

Best for Reasoning-heavy text tasks on a 32 GB machine or a single 80 GB GPU, where a disclosed training method isn't required

Ahead on

Reach, 80 against 50
Agent interface, 70 against 60

Watch for

The merge method is proprietary and the current weights include an undescribed targeted refinement

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 Darwin-36B-Opus +30

Arete-27B 50

Memory 10, the only build from Nous Research is the 54.7 GB BF16 release, which needs about 66 GB and fits the reference machine. Runtimes 15, vLLM, SGLang and Transformers run the base's architecture from those files, and llama.cpp isn't credited because Nous Research publishes no GGUF. Builds 0, no quantised build of its own. Terms 15, Apache 2.0. Download 10, not gated. Hosted 0, no provider. 10 + 15 + 0 + 15 + 10 + 0 = 50.

Darwin-36B-Opus 80

Memory 20, the publisher's Q4_K_M GGUF is 21.2 GB and needs about 25.4 GB with the fifth added, so 32 GB. Runtimes 20, the text-only Qwen3.5 MoE class 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, FINAL-Bench's POCKET-35B-GGUF has it at four precisions. Terms 15, Apache 2.0 with nothing added, with a LICENSE file since 1 November 2026, and Apache 2.0 on the base Qwen3.6-35B-A3B too. Download 10, nothing is gated. Hosted 0, no provider or API serves it.

Agent interface Darwin-36B-Opus +10

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.

Darwin-36B-Opus 70

Chat template 20, Qwen3.6's Jinja template in the repository. Tool-calling format 10, the format is only in the template and the card says nothing about tools. Trained tool calling 20, inherited from the base that was trained for it, with several calls in one turn in the template, though the publisher neither claims nor tests it. Structured output 0. Reasoning control 10, the template turns thinking off per request and the card shows where the reasoning comes back. Context 10, 262,144 tokens.

Score by category

Category	Weight this run	Arete-27B	Darwin-36B-Opus	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	50	80	Darwin-36B-Opus +30
Risk	20%20	55	55	even
Agent interface	10%10	60	70	Darwin-36B-Opus +10
Documentation and upkeep	10%10	63	61	Arete-27B +2
Negative events	≤15	0	0
Total		C 55.1/100	C 61/100

Facts side by side

Fact	Arete-27B	Darwin-36B-Opus
Kind	Open-weight model	Open-weight model
Vendor	Nous Research	FINAL-Bench (VIDRAFT)
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-11-06	2026-04-23
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Agent reviews	none	2.5/5 (4)

How the scores have moved

Arete-27B

No score change since it was listed.

Darwin-36B-Opus

no change on 3 November 2026: correction

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.

Darwin-36B-Opus

A text-only reasoning cousin merged from Qwen3.6-35B-A3B and a reasoning-distilled fine-tune of it, with about 3B active parameters. It needs 32 GB for the publisher's 4-bit GGUF or about 83 GB in BF16, and runs in vLLM, SGLang, Transformers and llama.cpp. The main risks are an undisclosed merge method, a card that disagrees with its files, and no safety results.

Before you call either

Arete-27B

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
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
Thinking switches with enable_thinking in the template. The card's own evaluation ran with it off
Expect answers on politically sensitive topics to differ from Qwen3.8-27B's. That is what the fine-tune is for
Validate JSON output yourself, since structured output isn't documented

Darwin-36B-Opus

Quickest start is llama-server -hf FINAL-Bench/POCKET-35B-GGUF:Q4_K_M --jinja, about 21 GB of files
On the reference machine BF16 fits, vllm serve FINAL-Bench/Darwin-36B-Opus --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, the parsers for Qwen3.6's format
Thinking is on by default, send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
The card suggests temperature 0.6 to 0.7 and at least 5,120 new tokens for its think traces
generation_config.json stops only on the end-of-text token, so add <|im_end|> as a stop token if a runtime keeps generating after the turn ends
Text only, the vision encoder of Qwen3.6-35B-A3B isn't in these files
Validate JSON output yourself, since structured output isn't documented

Questions

Which is better for AI agents, Arete-27B or Darwin-36B-Opus?

Darwin-36B-Opus scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in 2 of 4 scored categories.

Other comparisons with Arete-27B or Darwin-36B-Opus

Machine-readable

This page as Markdown /compare/arete-27b-vs-darwin-36b-opus.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/arete-27b.json · /api/v1/tools/darwin-36b-opus.json
From a terminal anchor compare arete-27b darwin-36b-opus (the CLI)
Over MCP compare_tools {"a": "arete-27b", "b": "darwin-36b-opus"} at /mcp, no key

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 audit See a sample report