Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 30B vs MiniMax-M2.5
Granite 4.2 30B scores 61 (C) on agent readiness against MiniMax-M2.5's 59 (C), and leads in every scored category. 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
Which one, for what
Best for Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 24 GB card
Ahead on
- Reach, 90 against 65
- Risk, 55 against 30
- Agent interface, 85 against 75
- Documentation and upkeep, 87 against 37
Watch for
No safety results published for it
Best for Teams with a 4 to 8 GPU server who want an open agent and coding model with parallel tool calls and can live with its use policy
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
230 GB in FP8, and about 155 GB for the smallest 4-bit library build, more than a 128 GB machine
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.
Documentation and upkeep Granite 4.2 30B +50
Granite 4.2 30B 87
Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (30B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 30B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 15, the last commit to the repository was on 4 September 2026, 67 days before this check. Responsiveness 20, Of the 4 discussions that aren't pull requests (28 August to 3 November 2026), 3 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 30B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 15 + 20 + 5 + 10 = 87.
MiniMax-M2.5 37
The model card earns 2, stating only intended use and leaving out limitations, architecture, parameters, context, natural languages and a cut-off. Training data earns 5 for a general description with no cut-off. The last change earns 20, a card edit on 26 October 2026 (commit 2515a3ea, a link renamed from MiniMax Agent to MiniMax Code), 9 days before this check; the files, template and code are unchanged since February. Responsiveness earns 5, with a MiniMax reply in 2 of the 40 most recent discussions and none since April. Version policy earns 5, since earlier and later models sit in their own repositories without dated notes. File health earns nothing, because the card's licence metadata still contradicts the licence in the files and an FP8 output report still waits without a reply. 2+5+20+5+5+0 = 37.
Reach Granite 4.2 30B +25
Granite 4.2 30B 90
Memory 25, IBM's own 4-bit MLX build granite-4.2-30b-q4-mlx is 16.47 GB, and 16.47 GB × 1.2 = 19.8 GB, which fits 24 GB but not 16 GB. Its Q4_0 GGUF is 16.58 GB and Ollama's library build granite4.2:30b 18 GB, the same band. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 30b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 25 + 25 + 15 + 15 + 10 + 0 = 90.
MiniMax-M2.5 65
Memory earns 5. MiniMax only publishes its 230 GB FP8 release, and the smallest build of 4-bit or better from a runtime's own library is LM Studio's MLX 4-bit at 128.7 GB, about 154 GB with the fifth added, so it needs more than our 107.4 GB machine and fits within 256 GB. Runtimes earn the full 25, with model code in released vLLM v0.33.0, SGLang v0.5.23, llama.cpp and Transformers, an LM Studio catalogue entry, and Ollama 0.40.14, whose pinned llama.cpp b11963 has the minimax-m2 architecture, though Ollama's library lists no build. Builds earn 10 for one publisher precision, the FP8 release. Terms earn 10 for a custom licence that allows free commercial use under a use policy. Download earns 10, with no gate or account. Hosted earns 5, since Novita and Featherless AI serve it through Hugging Face, while MiniMax's own API is closed to new users and retires it on 18 November 2026. 5+25+10+10+10+5 = 65.
Risk Granite 4.2 30B +25
Granite 4.2 30B 55
File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs and the GitHub README link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and the card's licence link resolves. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the 3B listing on 4 November 2026 (5). 15 + 15 + 0 + 5 + 15 + 5 = 55.
MiniMax-M2.5 30
File safety earns 15, safetensors only with no pickle files, less 10 because every documented loading route passes trust_remote_code for the repository's Python. Provenance earns the full 15, files in the organisation MiniMax links to with a SHA-256 for each shard. Safety evaluation and agent guidance earn nothing, as MiniMax publishes neither. Licence risk earns nothing (read 21 October 2026). The Prohibited Uses Policy goes beyond the law, MiniMax can end the licence for any breach and replaced its terms three weeks after release, and that change on 6 March 2026 came with no dated note while the card still links to a deleted file. The security programme earns nothing, with no security.txt, disclosure policy, SECURITY.md or advisories, and only a general contact address on the card.
Agent interface Granite 4.2 30B +10
Granite 4.2 30B 85
Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.
MiniMax-M2.5 75
The chat template earns 20 for chat_template.jinja in the repository. The tool-calling format earns 25, as MiniMax's own guide documents how tools go in and how calls come back, gives a parsing function, and its deployment guides name the vLLM and SGLang parsers. Trained tool calling earns 20, with several invoke blocks in one call. Structured output earns nothing, since JSON output isn't documented or claimed. Reasoning control earns nothing, because thinking is always on with no documented way to turn it off or budget it. Context earns 10 for 196,608 tokens with no position scaling.
Score by category
| Category | Weight this run | Granite 4.2 30B | MiniMax-M2.5 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 65 | Granite 4.2 30B +25 |
| Risk | 20%20 | 55 | 30 | Granite 4.2 30B +25 |
| Agent interface | 10%10 | 85 | 75 | Granite 4.2 30B +10 |
| Documentation and upkeep | 10%10 | 87 | 37 | Granite 4.2 30B +50 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 59/100 |
Facts side by side
| Fact | Granite 4.2 30B | MiniMax-M2.5 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | MiniMax |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MiniMax Model License (model) and modified MIT (code) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-04 | 2026-02-12 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 1.8/5 (4) |
How the scores have moved
Granite 4.2 30B
No score change since it was listed.
Verdicts
Granite 4.2 30B
IBM's largest reasoning cousin, with the same strengths as the 3B. It runs in every runtime we count from IBM's own builds on a 24 GB card, is signed, plain Apache 2.0, and comes with a disclosure of its training data. No safety results are published and structured output isn't documented.
MiniMax-M2.5
MiniMax-M2.5 is a 230B mixture-of-experts model for coding and agent work, with parallel tool calls, a 196K context and parsers in vLLM and SGLang. It needs a 4-GPU server for FP8 or about 155 GB for a 4-bit build. The main risk is a licence replaced after release with a Prohibited Uses Policy while the card still says modified MIT.
Before you call either
Granite 4.2 30B
- Start it with
ollama run granite4.2:30b, orllama-server -hf ibm-granite/granite-4.2-30b-GGUF:Q4_K_M --jinja - With vLLM 0.32.0 or later leave out
--reasoning-parser-plugin, since the parser is built in, and use--tool-call-parser qwen3_coder - Thinking is on by default. Pass
enable_thinkingfalse to turn it off orlow_efforttrue for short reasoning - The context is 131,072 tokens. The card's 512K extension isn't documented
- Validate JSON output yourself, since structured output isn't documented
- IBM recommends Granite Guardian beside it to flag risky inputs and outputs
MiniMax-M2.5
- Start it with vLLM on 4 GPUs of 96 GB, SAFETENSORS_FAST_GPU=1 vllm serve MiniMaxAI/MiniMax-M2.5 --trust-remote-code --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2_append_think
- In SGLang use --tool-call-parser minimax-m2 and --reasoning-parser minimax-append-think, with --trust-remote-code
- MiniMax's guides budget 220 GB for the weights and 240 GB per 1M tokens of KV cache
- On a single large-memory machine, LM Studio's catalogue entry minimax/minimax-m2.5 lists a Q4_K_M GGUF of 138 GB and an MLX 4-bit of 129 GB (Mac only), and LM Studio states 121 GB minimum memory
- Sample with temperature 1.0, top_p 0.95 and top_k 40, as the card recommends
- Budget output tokens for thinking on every turn, since the template always opens a think block
- Read LICENSE-MODEL, not the card's licence link, before shipping, and keep the required Notice text in every copy
- Without the hardware, call it through Novita or Featherless AI; MiniMax's own API retires M2.5 on 18 November 2026
Questions
Which is better for AI agents, Granite 4.2 30B or MiniMax-M2.5?
Granite 4.2 30B scores 61 (C) on agent readiness against MiniMax-M2.5's 59 (C), and leads in every scored category.
Other comparisons with Granite 4.2 30B or MiniMax-M2.5
- Agents-A1-4B vs Granite 4.2 30B
- Agents-A1-4B vs MiniMax-M2.5
- Apertus v1.5 8B vs Granite 4.2 30B
- Apertus v1.5 8B vs MiniMax-M2.5
- Apodex-1.1-mini vs Granite 4.2 30B
- Apodex-1.1-mini vs MiniMax-M2.5
- Arete-27B vs Granite 4.2 30B
- Arete-27B vs MiniMax-M2.5
- BigBang-v1 vs Granite 4.2 30B
- BigBang-v1 vs MiniMax-M2.5
- Carbon-X vs Granite 4.2 30B
- Carbon-X vs MiniMax-M2.5
- Cosmos-Reason2-2B vs Granite 4.2 30B
- Cosmos-Reason2-2B vs MiniMax-M2.5
- Darwin-36B-Opus vs Granite 4.2 30B
- Darwin-36B-Opus vs MiniMax-M2.5
- DeepSeek-V3.2 vs Granite 4.2 30B
- DeepSeek-V3.2 vs MiniMax-M2.5
- DeepSeek V4.1 Flash vs Granite 4.2 30B
- DeepSeek V4.1 Flash vs MiniMax-M2.5
- DeepSeek-V4-Flash-0731 vs Granite 4.2 30B
- DeepSeek-V4-Flash-0731 vs MiniMax-M2.5
- DiffusionGemma 26B A4B IT vs Granite 4.2 30B
- DiffusionGemma 26B A4B IT vs MiniMax-M2.5
- Gemma 4 12B IT vs Granite 4.2 30B
- Gemma 4 12B IT vs MiniMax-M2.5
- Gemma 4 26B A4B IT vs Granite 4.2 30B
- Gemma 4 26B A4B IT vs MiniMax-M2.5
- Gemma 4 31B IT vs Granite 4.2 30B
- Gemma 4 31B IT vs MiniMax-M2.5
- Gemma 4 E2B IT vs Granite 4.2 30B
- Gemma 4 E2B IT vs MiniMax-M2.5
- Gemma 4 E4B IT vs Granite 4.2 30B
- Gemma 4 E4B IT vs MiniMax-M2.5
- GLM-4.5-Air vs Granite 4.2 30B
- GLM-4.5-Air vs MiniMax-M2.5
- GLM-4.7-Flash vs Granite 4.2 30B
- GLM-4.7-Flash vs MiniMax-M2.5
- GLM-5.3-Flash vs Granite 4.2 30B
- GLM-5.3-Flash vs MiniMax-M2.5
- GLM-5.3 vs Granite 4.2 30B
- GLM-5.3 vs MiniMax-M2.5
- gpt-oss-120b vs Granite 4.2 30B
- gpt-oss-120b vs MiniMax-M2.5
- gpt-oss-20b vs Granite 4.2 30B
- gpt-oss-20b vs MiniMax-M2.5
- Granite 4.2 30B vs Granite 4.2 3B
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs Hy-Memory-30B-A3B
- Granite 4.2 30B vs Hy3
- Granite 4.2 30B vs Inkling
- Granite 4.2 30B vs Inkling-Small
- Granite 4.2 30B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 30B vs Kimi K3
- Granite 4.2 30B vs Kimi K3.1 Pro
- Granite 4.2 30B vs Kolibri-1
- Granite 4.2 30B vs Kronos
- Granite 4.2 30B vs Laguna M.1
- Granite 4.2 30B vs Laguna S 2.1
- Granite 4.2 30B vs Laguna XS 2.1
- Granite 4.2 30B vs LBS-27B
- Granite 4.2 30B vs LFM2.5-2.6B
- Granite 4.2 30B vs LFM3-1.7B
- Granite 4.2 30B vs LFM3-Audio-2B
- Granite 4.2 30B vs LFM3-Omni-2B
- Granite 4.2 30B vs LFM3-VL-2B
- Granite 4.2 30B vs Ling-3.0-tiny
- Granite 4.2 30B vs Ling-3.1-flash-1019
- Granite 4.2 30B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 30B vs MiniCPM-o 4.5
- Granite 4.2 30B vs MiniCPM-V 4.7 1B
- Granite 4.2 30B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 30B vs MiniCPM5-2B
- Granite 4.2 30B vs MiniMax-M2.7
- Granite 4.2 30B vs MiniMax-M3.1-Flash
- Granite 4.2 30B vs Mistral Large 4
- Granite 4.2 30B vs Muse Glimmer 30B
- Granite 4.2 30B vs Nanbeige4.3-33B
- Granite 4.2 30B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 30B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 30B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 30B vs Nemotron 3 Nano 4B
- Granite 4.2 30B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 30B vs Nemotron 3 Super 120B A12B
- Granite 4.2 30B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 30B vs occamy-1.0
- Granite 4.2 30B vs Olmo 3 7B Think
- Granite 4.2 30B vs Ornith-1.5-122B
- Granite 4.2 30B vs Ornith-1.5-35B-A3B
- Granite 4.2 30B vs Ornith-1.5-397B
- Granite 4.2 30B vs Ornith-1.5-9B
- Granite 4.2 30B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 30B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 30B vs Qwen3-4B-Instruct-2507
- Granite 4.2 30B vs Qwen3.5-0.8B
- Granite 4.2 30B vs Qwen3.5-122B-A10B
- Granite 4.2 30B vs Qwen3.5-2B
- Granite 4.2 30B vs Qwen3.5-397B-A17B
- Granite 4.2 30B vs Qwen3.5-4B
- Granite 4.2 30B vs Qwen3.5-9B
- Granite 4.2 30B vs Qwen3.6-27B
- Granite 4.2 30B vs Qwen3.6-35B-A3B
- Granite 4.2 30B vs Qwen3.8-27B
- Granite 4.2 30B vs Qwen3.8-Flash-Next
- Granite 4.2 30B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 30B vs Qwen3-Coder-Next
- Granite 4.2 30B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 30B vs Qwen3-VL-2B-Instruct
- Granite 4.2 30B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 30B vs Qwen3-VL-32B-Instruct
- Granite 4.2 30B vs Qwen3-VL-4B-Instruct
- Granite 4.2 30B vs Qwen3-VL-8B-Instruct
- Granite 4.2 30B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 30B vs Recursive Flint
- Granite 4.2 30B vs Ripple-65B Preview
- Granite 4.2 30B vs SmolLM3-3B
- Granite 4.2 30B vs Spark-X2.6-4B
- Granite 4.2 30B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 30B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 30B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 30B vs Baidu Unlimited-OCR-2
- Granite 4.2 3B vs MiniMax-M2.5
- Granite 4.2 8B vs MiniMax-M2.5
- Hy-Memory-30B-A3B vs MiniMax-M2.5
- Hy3 vs MiniMax-M2.5
- Inkling-Small vs MiniMax-M2.5
- Inkling vs MiniMax-M2.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniMax-M2.5
- Kimi K3.1 Pro vs MiniMax-M2.5
- Kimi K3 vs MiniMax-M2.5
- Kolibri-1 vs MiniMax-M2.5
- Kronos vs MiniMax-M2.5
- Laguna M.1 vs MiniMax-M2.5
- Laguna S 2.1 vs MiniMax-M2.5
- Laguna XS 2.1 vs MiniMax-M2.5
- LBS-27B vs MiniMax-M2.5
- LFM2.5-2.6B vs MiniMax-M2.5
- LFM3-1.7B vs MiniMax-M2.5
- LFM3-Audio-2B vs MiniMax-M2.5
- LFM3-Omni-2B vs MiniMax-M2.5
- LFM3-VL-2B vs MiniMax-M2.5
- Ling-3.0-tiny vs MiniMax-M2.5
- Ling-3.1-flash-1019 vs MiniMax-M2.5
- MiMo-V2.6 Distill Qwen 9B vs MiniMax-M2.5
- MiniCPM-o 4.5 vs MiniMax-M2.5
- MiniCPM-V 4.7 1B vs MiniMax-M2.5
- MiniCPM-V 4.7 35B-A3B vs MiniMax-M2.5
- MiniCPM5-2B vs MiniMax-M2.5
- MiniMax-M2.5 vs MiniMax-M2.7
- MiniMax-M2.5 vs MiniMax-M3.1-Flash
- MiniMax-M2.5 vs Mistral Large 4
- MiniMax-M2.5 vs Muse Glimmer 30B
- MiniMax-M2.5 vs Nanbeige4.3-33B
- MiniMax-M2.5 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- MiniMax-M2.5 vs Nemotron 3.5 Lightning 30B A3B
- MiniMax-M2.5 vs Nemotron 3 Nano 30B A3B
- MiniMax-M2.5 vs Nemotron 3 Nano 4B
- MiniMax-M2.5 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniMax-M2.5 vs Nemotron 3 Super 120B A12B
- MiniMax-M2.5 vs Nemotron 3 Ultra 550B A55B
- MiniMax-M2.5 vs occamy-1.0
- MiniMax-M2.5 vs Olmo 3 7B Think
- MiniMax-M2.5 vs Ornith-1.5-122B
- MiniMax-M2.5 vs Ornith-1.5-35B-A3B
- MiniMax-M2.5 vs Ornith-1.5-397B
- MiniMax-M2.5 vs Ornith-1.5-9B
- MiniMax-M2.5 vs Qwen-AgentWorld-35B-A3B
- MiniMax-M2.5 vs Qwen3-30B-A3B-Instruct-2507
- MiniMax-M2.5 vs Qwen3-4B-Instruct-2507
- MiniMax-M2.5 vs Qwen3.5-0.8B
- MiniMax-M2.5 vs Qwen3.5-122B-A10B
- MiniMax-M2.5 vs Qwen3.5-2B
- MiniMax-M2.5 vs Qwen3.5-397B-A17B
- MiniMax-M2.5 vs Qwen3.5-4B
- MiniMax-M2.5 vs Qwen3.5-9B
- MiniMax-M2.5 vs Qwen3.6-27B
- MiniMax-M2.5 vs Qwen3.6-35B-A3B
- MiniMax-M2.5 vs Qwen3.8-27B
- MiniMax-M2.5 vs Qwen3.8-Flash-Next
- MiniMax-M2.5 vs Qwen3-Coder-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-Coder-Next
- MiniMax-M2.5 vs Qwen3-Omni-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-2B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-32B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-4B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-8B-Instruct
- MiniMax-M2.5 vs Qwopus3.8-27B-Flash-V2
- MiniMax-M2.5 vs Recursive Flint
- MiniMax-M2.5 vs Ripple-65B Preview
- MiniMax-M2.5 vs SmolLM3-3B
- MiniMax-M2.5 vs Spark-X2.6-4B
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-Flash-Next
- MiniMax-M2.5 vs ThinkingCap (Qwen3.8 27B)
- MiniMax-M2.5 vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-30b-vs-minimax-m2-5.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-30b.json·/api/v1/tools/minimax-m2-5.json - From a terminal
anchor compare granite-4-2-30b minimax-m2-5(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-30b", "b": "minimax-m2-5"}at/mcp, no key