Head to head · Open-weight models you run yourself · October 2026 research run
Devstral Small 2 vs Inkling 2 Mini
Devstral Small 2 and Inkling 2 Mini score within a point of each other on agent readiness, 61 (C) and 61 (C). Inkling 2 Mini leads on risk, agent interface and documentation and upkeep. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6586 open weights comparisons
Which one, for what
Best for Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac
Ahead on
- Reach, 90 against 60
Watch for
No limitations, safety results, languages or data on the card
Best for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build.
Ahead on
- Risk, 70 against 60
- Agent interface, 85 against 65
- Documentation and upkeep, 57 against 46
Watch for
No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026
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 Devstral Small 2 +30
Devstral Small 2 90
Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.
Inkling 2 Mini 60
Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added. Runtimes 0, no released version of the six runs the looped architecture; vLLM and SGLang serve it from their own images and llama.cpp has it on master only. Builds 10, one checkpoint from the publisher in mixed NVFP4 and MXFP8. Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker samples from it. 25 + 0 + 10 + 10 + 10 + 5 = 60.
Agent interface Inkling 2 Mini +20
Devstral Small 2 65
Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokeniser's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.
Inkling 2 Mini 85
Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, tml-renderers renders and parses it, and vLLM and SGLang name their parsers. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, reasoning_effort per request. Context 10, 1M trained. 20 + 25 + 20 + 0 + 10 + 10 = 85.
Documentation and upkeep Inkling 2 Mini +11
Devstral Small 2 46
Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokeniser and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.
Inkling 2 Mini 57
Model card 17, no knowledge cut-off. Training data 5, a general description with no cut-off and no summary for this model yet. Last change 20, uploaded today. Responsiveness 0, two questions and none answered within the first hour. Version policy 5, a first release. File health 10, the files and the card agree. 17 + 5 + 20 + 0 + 5 + 10 = 57.
Risk Inkling 2 Mini +10
Devstral Small 2 60
File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.
Inkling 2 Mini 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 evaluations and monitorability results, nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what the safety work covered and names safeguards for agent use (a sandbox, confirmation before destructive actions), 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 5, security.txt and a disclosure policy. 25 + 15 + 10 + 10 + 5 + 5 = 70.
Score by category
| Category | Weight | Devstral Small 2 | Inkling 2 Mini | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 90 | 60 | Devstral Small 2 +30 |
| Risk | 20% | 60 | 70 | Inkling 2 Mini +10 |
| Agent interface | 10% | 65 | 85 | Inkling 2 Mini +20 |
| Documentation and upkeep | 10% | 46 | 57 | Inkling 2 Mini +11 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Devstral Small 2 | Inkling 2 Mini |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Mistral AI | Thinking Machines Lab |
| 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 | 2026-07-15 | 2026-11-20 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
Verdicts
Devstral Small 2
The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.
Inkling 2 Mini
Thinking Machines' small open model, a looped 26.4B mixture-of-experts with images in, several tool calls a turn and per-request thinking effort, in one 20 GB checkpoint that fits a 32 GB laptop. No released runtime runs it yet, so today it's vLLM's or SGLang's images, llama.cpp from master, or Tinker.
Before you call either
Devstral Small 2
ollama run devstral-small-2is the quickest start, at 15 GB- On vLLM pass
--tool-call-parser mistral --enable-auto-tool-choice - Send the system prompt from CHAT_SYSTEM_PROMPT.txt in the repository. The card says results depend on it
- Use a low temperature. The repository's default is 0.15
- Plan for one tool call per turn
- The same model is on our Mistral API listing if you'd rather not host it
Inkling 2 Mini
- No released runtime runs it yet. Serve it from vLLM's vllm/vllm-openai:inkling-2-mini image with
--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling, or from SGLang's lmsysorg/sglang:inkling-2-mini image, where the tool-call parser isinkling2 - On a laptop, ggml-org's GGUF runs in a llama.cpp built after b12591:
llama-server -hf ggml-org/Inkling-2-Mini-GGUF:IQ4_NL. The looped architecture isn't in a llama.cpp release yet - Pass
reasoning_effortas none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99. The minimum doesn't fully turn reasoning off - The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
- Run it in a sandbox and confirm destructive actions: the card says it may delete or overwrite files without asking and misreport what it did
- Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
- Images should be 40 to 4096 px a side. It takes no audio, and the template raises an error for an audio part
- Use guided decoding or validate JSON yourself, since structured output isn't documented
- Without the hardware, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
- 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, Devstral Small 2 or Inkling 2 Mini?
Devstral Small 2 and Inkling 2 Mini score within a point of each other on agent readiness, 61 (C) and 61 (C). Inkling 2 Mini leads on risk, agent interface and documentation and upkeep.
Other comparisons with Devstral Small 2 or Inkling 2 Mini
- Agents-A1-4B vs Devstral Small 2
- Agents-A1-4B vs Inkling 2 Mini
- Apertus v1.5 8B vs Devstral Small 2
- Apertus v1.5 8B vs Inkling 2 Mini
- Apodex-1.1-mini vs Devstral Small 2
- Apodex-1.1-mini vs Inkling 2 Mini
- Arete-27B vs Devstral Small 2
- Arete-27B vs Inkling 2 Mini
- BigBang-v1 vs Devstral Small 2
- BigBang-v1 vs Inkling 2 Mini
- Carbon-X vs Devstral Small 2
- Carbon-X vs Inkling 2 Mini
- Cola2 vs Devstral Small 2
- Cola2 vs Inkling 2 Mini
- Cosmos-Reason2-2B vs Devstral Small 2
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Darwin-36B-Opus vs Devstral Small 2
- Darwin-36B-Opus vs Inkling 2 Mini
- DeepSeek-V3.2 vs Devstral Small 2
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs Devstral Small 2
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs Devstral Small 2
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- Devstral Small 2 vs DiffusionGemma 26B A4B IT
- Devstral Small 2 vs EXAONE 4.5 33B
- Devstral Small 2 vs Gemma 4 12B IT
- Devstral Small 2 vs Gemma 4 26B A4B IT
- Devstral Small 2 vs Gemma 4 31B IT
- Devstral Small 2 vs Gemma 4 E2B IT
- Devstral Small 2 vs Gemma 4 E4B IT
- Devstral Small 2 vs GLM-4.5-Air
- Devstral Small 2 vs GLM-4.7-Flash
- Devstral Small 2 vs GLM-5.3
- Devstral Small 2 vs GLM-5.3-Flash
- Devstral Small 2 vs gpt-oss-120b
- Devstral Small 2 vs gpt-oss-20b
- Devstral Small 2 vs Granite 4.2 30B
- Devstral Small 2 vs Granite 4.2 3B
- Devstral Small 2 vs Granite 4.2 8B
- Devstral Small 2 vs Hy-Memory-30B-A3B
- Devstral Small 2 vs Hy3
- Devstral Small 2 vs Inkling
- Devstral Small 2 vs Inkling 2 Small
- Devstral Small 2 vs Inkling-Small
- Devstral Small 2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Devstral Small 2 vs Kimi K3
- Devstral Small 2 vs Kimi K3.1 Pro
- Devstral Small 2 vs Kolibri-1
- Devstral Small 2 vs Kronos
- Devstral Small 2 vs Laguna M.1
- Devstral Small 2 vs Laguna S 2.1
- Devstral Small 2 vs Laguna XS 2.1
- Devstral Small 2 vs LBS-27B
- Devstral Small 2 vs LFM2.5-2.6B
- Devstral Small 2 vs LFM3-1.7B
- Devstral Small 2 vs LFM3-Audio-2B
- Devstral Small 2 vs LFM3-Omni-2B
- Devstral Small 2 vs LFM3-VL-2B
- Devstral Small 2 vs Ling-3.0-tiny
- Devstral Small 2 vs Ling-3.1-flash-1019
- Devstral Small 2 vs LongCat-2.5
- Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B
- Devstral Small 2 vs MiMo-V2.6-Flash-RL
- Devstral Small 2 vs MiniCPM-o 4.5
- Devstral Small 2 vs MiniCPM-V 4.7 1B
- Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B
- Devstral Small 2 vs MiniCPM5-2B
- Devstral Small 2 vs MiniMax-M2.5
- Devstral Small 2 vs MiniMax-M2.7
- Devstral Small 2 vs MiniMax-M3.1-Flash
- Devstral Small 2 vs Mistral Large 4
- Devstral Small 2 vs Muse Glimmer 30B
- Devstral Small 2 vs Nanbeige4.2-3B
- Devstral Small 2 vs Nanbeige4.3-33B
- Devstral Small 2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Devstral Small 2 vs Nemotron 3.5 Lightning 30B A3B
- Devstral Small 2 vs Nemotron 3 Nano 30B A3B
- Devstral Small 2 vs Nemotron 3 Nano 4B
- Devstral Small 2 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Devstral Small 2 vs Nemotron 3 Super 120B A12B
- Devstral Small 2 vs Nemotron 3 Ultra 550B A55B
- Devstral Small 2 vs North Mini Code 1.0
- Devstral Small 2 vs occamy-1.0
- Devstral Small 2 vs Olmo 3 7B Think
- Devstral Small 2 vs Ornith-1.5-122B
- Devstral Small 2 vs Ornith-1.5-35B-A3B
- Devstral Small 2 vs Ornith-1.5-397B
- Devstral Small 2 vs Ornith-1.5-9B
- Devstral Small 2 vs OTel-2.0-LLM-31B-IT
- Devstral Small 2 vs Qwen-AgentWorld-35B-A3B
- Devstral Small 2 vs Qwen3-30B-A3B-Instruct-2507
- Devstral Small 2 vs Qwen3-4B-Instruct-2507
- Devstral Small 2 vs Qwen3.5-0.8B
- Devstral Small 2 vs Qwen3.5-122B-A10B
- Devstral Small 2 vs Qwen3.5-2B
- Devstral Small 2 vs Qwen3.5-397B-A17B
- Devstral Small 2 vs Qwen3.5-4B
- Devstral Small 2 vs Qwen3.5-9B
- Devstral Small 2 vs Qwen3.6-27B
- Devstral Small 2 vs Qwen3.6-35B-A3B
- Devstral Small 2 vs Qwen3.8-27B
- Devstral Small 2 vs Qwen3.8-Flash-Next
- Devstral Small 2 vs Qwen3-Coder-30B-A3B-Instruct
- Devstral Small 2 vs Qwen3-Coder-Next
- Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct
- Devstral Small 2 vs Qwen3-VL-2B-Instruct
- Devstral Small 2 vs Qwen3-VL-30B-A3B-Instruct
- Devstral Small 2 vs Qwen3-VL-32B-Instruct
- Devstral Small 2 vs Qwen3-VL-4B-Instruct
- Devstral Small 2 vs Qwen3-VL-8B-Instruct
- Devstral Small 2 vs Qwopus3.8-27B-Flash-V2
- Devstral Small 2 vs Recursive Flint
- Devstral Small 2 vs Ripple-65B Preview
- Devstral Small 2 vs SenseNova-Loop-9B-Preview
- Devstral Small 2 vs SmolLM3-3B
- Devstral Small 2 vs Spark-X2.6-4B
- Devstral Small 2 vs Step 3.7 Flash
- Devstral Small 2 vs Swift 1.5 Qwen3.8-27B
- Devstral Small 2 vs Swift 1.5 Qwen3.8-Flash-Next
- Devstral Small 2 vs ThinkingCap (Qwen3.8 27B)
- Devstral Small 2 vs Baidu Unlimited-OCR-2
- Devstral Small 2 vs WeVisOne-VL-2B
- Devstral Small 2 vs WeVisOne-VL-4B
- Devstral Small 2 vs ZAYA1-8B
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- EXAONE 4.5 33B vs Inkling 2 Mini
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs Inkling 2 Mini
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3 vs Inkling 2 Mini
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-20b vs Inkling 2 Mini
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 8B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy3 vs Inkling 2 Mini
- Inkling 2 Mini vs Inkling 2 Small
- Inkling 2 Mini vs Inkling-Small
- Inkling 2 Mini vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling 2 Mini vs Kimi K3
- Inkling 2 Mini vs Kimi K3.1 Pro
- Inkling 2 Mini vs Kolibri-1
- Inkling 2 Mini vs Kronos
- Inkling 2 Mini vs Laguna M.1
- Inkling 2 Mini vs Laguna S 2.1
- Inkling 2 Mini vs Laguna XS 2.1
- Inkling 2 Mini vs LBS-27B
- Inkling 2 Mini vs LFM2.5-2.6B
- Inkling 2 Mini vs LFM3-1.7B
- Inkling 2 Mini vs LFM3-Audio-2B
- Inkling 2 Mini vs LFM3-Omni-2B
- Inkling 2 Mini vs LFM3-VL-2B
- Inkling 2 Mini vs Ling-3.0-tiny
- Inkling 2 Mini vs Ling-3.1-flash-1019
- Inkling 2 Mini vs LongCat-2.5
- Inkling 2 Mini vs MiMo-V2.6 Distill Qwen 9B
- Inkling 2 Mini vs MiMo-V2.6-Flash-RL
- Inkling 2 Mini vs MiniCPM-o 4.5
- Inkling 2 Mini vs MiniCPM-V 4.7 1B
- Inkling 2 Mini vs MiniCPM-V 4.7 35B-A3B
- Inkling 2 Mini vs MiniCPM5-2B
- Inkling 2 Mini vs MiniMax-M2.5
- Inkling 2 Mini vs MiniMax-M2.7
- Inkling 2 Mini vs MiniMax-M3.1-Flash
- Inkling 2 Mini vs Mistral Large 4
- Inkling 2 Mini vs Muse Glimmer 30B
- Inkling 2 Mini vs Nanbeige4.2-3B
- Inkling 2 Mini vs Nanbeige4.3-33B
- Inkling 2 Mini vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling 2 Mini vs Nemotron 3.5 Lightning 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 4B
- Inkling 2 Mini vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling 2 Mini vs Nemotron 3 Super 120B A12B
- Inkling 2 Mini vs Nemotron 3 Ultra 550B A55B
- Inkling 2 Mini vs North Mini Code 1.0
- Inkling 2 Mini vs occamy-1.0
- Inkling 2 Mini vs Olmo 3 7B Think
- Inkling 2 Mini vs Ornith-1.5-122B
- Inkling 2 Mini vs Ornith-1.5-35B-A3B
- Inkling 2 Mini vs Ornith-1.5-397B
- Inkling 2 Mini vs Ornith-1.5-9B
- Inkling 2 Mini vs OTel-2.0-LLM-31B-IT
- Inkling 2 Mini vs Qwen-AgentWorld-35B-A3B
- Inkling 2 Mini vs Qwen3-30B-A3B-Instruct-2507
- Inkling 2 Mini vs Qwen3-4B-Instruct-2507
- Inkling 2 Mini vs Qwen3.5-0.8B
- Inkling 2 Mini vs Qwen3.5-122B-A10B
- Inkling 2 Mini vs Qwen3.5-2B
- Inkling 2 Mini vs Qwen3.5-397B-A17B
- Inkling 2 Mini vs Qwen3.5-4B
- Inkling 2 Mini vs Qwen3.5-9B
- Inkling 2 Mini vs Qwen3.6-27B
- Inkling 2 Mini vs Qwen3.6-35B-A3B
- Inkling 2 Mini vs Qwen3.8-27B
- Inkling 2 Mini vs Qwen3.8-Flash-Next
- Inkling 2 Mini vs Qwen3-Coder-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-Coder-Next
- Inkling 2 Mini vs Qwen3-Omni-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-2B-Instruct
- Inkling 2 Mini vs Qwen3-VL-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-32B-Instruct
- Inkling 2 Mini vs Qwen3-VL-4B-Instruct
- Inkling 2 Mini vs Qwen3-VL-8B-Instruct
- Inkling 2 Mini vs Qwopus3.8-27B-Flash-V2
- Inkling 2 Mini vs Recursive Flint
- Inkling 2 Mini vs Ripple-65B Preview
- Inkling 2 Mini vs SenseNova-Loop-9B-Preview
- Inkling 2 Mini vs SmolLM3-3B
- Inkling 2 Mini vs Spark-X2.6-4B
- Inkling 2 Mini vs Step 3.7 Flash
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-27B
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling 2 Mini vs ThinkingCap (Qwen3.8 27B)
- Inkling 2 Mini vs Baidu Unlimited-OCR-2
- Inkling 2 Mini vs WeVisOne-VL-2B
- Inkling 2 Mini vs WeVisOne-VL-4B
- Inkling 2 Mini vs ZAYA1-8B
- Inkling vs Inkling 2 Mini
Machine-readable
- This page as Markdown
/compare/devstral-small-2-vs-inkling-2-mini.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/devstral-small-2.json·/api/v1/tools/inkling-2-mini.json - From a terminal
anchor compare devstral-small-2 inkling-2-mini(the CLI) - Over MCP
compare_tools {"a": "devstral-small-2", "b": "inkling-2-mini"}at/mcp, no key