Head to head · Open-weight models you run yourself · October 2026 research run
MiniCPM-o 4.5 vs MiniCPM-V 4.7 35B-A3B
MiniCPM-o 4.5 and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on risk and agent interface. 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
Best conversational voice-agent APIs · All 581 voice agents comparisons
Which one, for what
Best for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Speech output and full duplex need trust_remote_code with Transformers 4.51.0 or OpenBMB's llama.cpp-omni
Best for Agents that need to read screenshots, documents and video on a local machine with 24 to 32 GB for the model, under a permissive licence
Ahead on
- Risk, 55 against 40
- Agent interface, 70 against 35
Watch for
No limitations section, safety results, agent-use guidance or security contact
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 MiniCPM-V 4.7 35B-A3B +35
MiniCPM-o 4.5 35
Chat template 20, a Jinja template in the tokenizer config. Tool-calling format 10 of 25, only the inherited Qwen3 template says how tools work. Trained tool calling 0, OpenBMB never mentions tool use. Structured output 0, not documented. Reasoning control 0, thinking turns on and off per request but nobody says where the reasoning comes back. Context 5, 40,960 tokens. Read as an omni model, it takes images, video and audio and returns text and streaming speech, which the card documents with code.
MiniCPM-V 4.7 35B-A3B 70
Chat template 20, a Jinja file in the repository. Tool-calling format 10, the card shows the tools array going in but not the call coming back, and names no parser. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, enable_thinking per request, off by default, with the trace between markers. Context 10, 262,144 tokens native.
Risk MiniCPM-V 4.7 35B-A3B +15
MiniCPM-o 4.5 40
File safety 5 of 25, two pickle files sit in the speech stage and the documented load runs repository code. Provenance 15, the files are in the openbmb organisation OpenBMB's GitHub links, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 5, general cautions only, nothing about voice cloning misuse, prompt injection or refusals. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt, policy or advisories.
MiniCPM-V 4.7 35B-A3B 55
File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed. Provenance 15, the files come from the openbmb organisation OpenBMB's GitHub README links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either, and the card has no limitations section. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt or SECURITY.md.
Score by category
| Category | Weight this run | MiniCPM-o 4.5 | MiniCPM-V 4.7 35B-A3B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 90 | even |
| Risk | 20%20 | 40 | 55 | MiniCPM-V 4.7 35B-A3B +15 |
| Agent interface | 10%10 | 35 | 70 | MiniCPM-V 4.7 35B-A3B +35 |
| Documentation and upkeep | 10%10 | 66 | 68 | MiniCPM-V 4.7 35B-A3B +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | MiniCPM-o 4.5 | MiniCPM-V 4.7 35B-A3B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | OpenBMB | OpenBMB |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-24 | 2026-11-03 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 2.8/5 (4) | none |
Verdicts
MiniCPM-o 4.5
A small omni cousin that sees, listens and talks back, with full-duplex speech and voice cloning, in about 7 GB at 4-bit through llama.cpp or Ollama for text and images. Speech output needs OpenBMB's remote code or llama.cpp-omni, and 28 GB of GPU for the full demo. The main risks are repository code and pickle files and no safety results.
MiniCPM-V 4.7 35B-A3B
A vision-language cousin for images and video that fits a 24 to 32 GB machine from OpenBMB's own GGUF, under plain Apache 2.0, with a publisher that answers. The card says little about limits, training data or how tool calls come back, so test the tool format in your runtime before relying on it.
Before you call either
MiniCPM-o 4.5
- Quickest start for text and images is
ollama run openbmb/minicpm-o4.5, about 6 GB - With vLLM 0.16.0 or later pass
--trust-remote-code, and sendstop_token_ids[151643, 151645] as OpenBMB's guide does - vLLM, llama.cpp and Ollama return text only; for speech out use the card's Transformers 4.51.0 code or OpenBMB's llama.cpp-omni
- In llama.cpp pass both the language GGUF and MiniCPM-o-4_5-vision-F16.gguf with
--mmproj, and use--jinja --reasoning-budget 0to turn thinking off - Keep prompts within 40,960 tokens
- Don't rely on tool calls or JSON output, neither is documented; validate any you get
MiniCPM-V 4.7 35B-A3B
- Start it with
llama-server -hf openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_M --jinja, orollama run openbmb/minicpm-v4.7:35b-a3b - For image input in llama.cpp add
mmproj-model-f16.gguf, or the 4x projector for more visual detail at a higher cost - The GGUF files at the repository root have thinking off. Use the files in
thinking/when you want the trace - With Transformers pass
enable_thinkingtoapply_chat_template, and passdownsample_modeto bothapply_chat_templateandgenerate - Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
- Check tool calls in your runtime first, since the card names no parser. The template uses the Qwen3.5 function-block format
- Validate JSON output yourself, since structured output isn't documented
Questions
Which is better for AI agents, MiniCPM-o 4.5 or MiniCPM-V 4.7 35B-A3B?
MiniCPM-o 4.5 and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on risk and agent interface.
Other comparisons with MiniCPM-o 4.5 or MiniCPM-V 4.7 35B-A3B
- Agents-A1-4B vs MiniCPM-o 4.5
- Agents-A1-4B vs MiniCPM-V 4.7 35B-A3B
- Apertus v1.5 8B vs MiniCPM-o 4.5
- Apertus v1.5 8B vs MiniCPM-V 4.7 35B-A3B
- Apodex-1.1-mini vs MiniCPM-o 4.5
- Apodex-1.1-mini vs MiniCPM-V 4.7 35B-A3B
- Arete-27B vs MiniCPM-o 4.5
- Arete-27B vs MiniCPM-V 4.7 35B-A3B
- BigBang-v1 vs MiniCPM-o 4.5
- BigBang-v1 vs MiniCPM-V 4.7 35B-A3B
- Carbon-X vs MiniCPM-o 4.5
- Carbon-X vs MiniCPM-V 4.7 35B-A3B
- Cola2 vs MiniCPM-o 4.5
- Cola2 vs MiniCPM-V 4.7 35B-A3B
- Cosmos-Reason2-2B vs MiniCPM-o 4.5
- Cosmos-Reason2-2B vs MiniCPM-V 4.7 35B-A3B
- Darwin-36B-Opus vs MiniCPM-o 4.5
- Darwin-36B-Opus vs MiniCPM-V 4.7 35B-A3B
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs MiniCPM-V 4.7 35B-A3B
- DeepSeek V4.1 Flash vs MiniCPM-o 4.5
- DeepSeek V4.1 Flash vs MiniCPM-V 4.7 35B-A3B
- DeepSeek-V4-Flash-0731 vs MiniCPM-o 4.5
- DeepSeek-V4-Flash-0731 vs MiniCPM-V 4.7 35B-A3B
- Devstral Small 2 vs MiniCPM-o 4.5
- Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B
- DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5
- DiffusionGemma 26B A4B IT vs MiniCPM-V 4.7 35B-A3B
- EXAONE 4.5 33B vs MiniCPM-o 4.5
- EXAONE 4.5 33B vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 12B IT vs MiniCPM-o 4.5
- Gemma 4 12B IT vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 E2B IT vs MiniCPM-o 4.5
- Gemma 4 E2B IT vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 E4B IT vs MiniCPM-o 4.5
- Gemma 4 E4B IT vs MiniCPM-V 4.7 35B-A3B
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.5-Air vs MiniCPM-V 4.7 35B-A3B
- GLM-4.7-Flash vs MiniCPM-o 4.5
- GLM-4.7-Flash vs MiniCPM-V 4.7 35B-A3B
- GLM-5.3-Flash vs MiniCPM-o 4.5
- GLM-5.3-Flash vs MiniCPM-V 4.7 35B-A3B
- GLM-5.3 vs MiniCPM-o 4.5
- GLM-5.3 vs MiniCPM-V 4.7 35B-A3B
- gpt-oss-120b vs MiniCPM-o 4.5
- gpt-oss-120b vs MiniCPM-V 4.7 35B-A3B
- gpt-oss-20b vs MiniCPM-o 4.5
- gpt-oss-20b vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 30B vs MiniCPM-o 4.5
- Granite 4.2 30B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 3B vs MiniCPM-o 4.5
- Granite 4.2 3B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 8B vs MiniCPM-o 4.5
- Granite 4.2 8B vs MiniCPM-V 4.7 35B-A3B
- Hy-Memory-30B-A3B vs MiniCPM-o 4.5
- Hy-Memory-30B-A3B vs MiniCPM-V 4.7 35B-A3B
- Hy3 vs MiniCPM-o 4.5
- Hy3 vs MiniCPM-V 4.7 35B-A3B
- Inkling-Small vs MiniCPM-o 4.5
- Inkling-Small vs MiniCPM-V 4.7 35B-A3B
- Inkling vs MiniCPM-o 4.5
- Inkling vs MiniCPM-V 4.7 35B-A3B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-V 4.7 35B-A3B
- Kimi K3.1 Pro vs MiniCPM-o 4.5
- Kimi K3.1 Pro vs MiniCPM-V 4.7 35B-A3B
- Kimi K3 vs MiniCPM-o 4.5
- Kimi K3 vs MiniCPM-V 4.7 35B-A3B
- Kolibri-1 vs MiniCPM-o 4.5
- Kolibri-1 vs MiniCPM-V 4.7 35B-A3B
- Kronos vs MiniCPM-o 4.5
- Kronos vs MiniCPM-V 4.7 35B-A3B
- Laguna M.1 vs MiniCPM-o 4.5
- Laguna M.1 vs MiniCPM-V 4.7 35B-A3B
- Laguna S 2.1 vs MiniCPM-o 4.5
- Laguna S 2.1 vs MiniCPM-V 4.7 35B-A3B
- Laguna XS 2.1 vs MiniCPM-o 4.5
- Laguna XS 2.1 vs MiniCPM-V 4.7 35B-A3B
- LBS-27B vs MiniCPM-o 4.5
- LBS-27B vs MiniCPM-V 4.7 35B-A3B
- LFM2.5-2.6B vs MiniCPM-o 4.5
- LFM2.5-2.6B vs MiniCPM-V 4.7 35B-A3B
- LFM3-1.7B vs MiniCPM-o 4.5
- LFM3-1.7B vs MiniCPM-V 4.7 35B-A3B
- LFM3-Audio-2B vs MiniCPM-o 4.5
- LFM3-Audio-2B vs MiniCPM-V 4.7 35B-A3B
- LFM3-Omni-2B vs MiniCPM-o 4.5
- LFM3-Omni-2B vs MiniCPM-V 4.7 35B-A3B
- LFM3-VL-2B vs MiniCPM-o 4.5
- LFM3-VL-2B vs MiniCPM-V 4.7 35B-A3B
- Ling-3.0-tiny vs MiniCPM-o 4.5
- Ling-3.0-tiny vs MiniCPM-V 4.7 35B-A3B
- Ling-3.1-flash-1019 vs MiniCPM-o 4.5
- Ling-3.1-flash-1019 vs MiniCPM-V 4.7 35B-A3B
- LongCat-2.5 vs MiniCPM-o 4.5
- LongCat-2.5 vs MiniCPM-V 4.7 35B-A3B
- MiMo-V2.6 Distill Qwen 9B vs MiniCPM-o 4.5
- MiMo-V2.6 Distill Qwen 9B vs MiniCPM-V 4.7 35B-A3B
- MiMo-V2.6-Flash-RL vs MiniCPM-o 4.5
- MiMo-V2.6-Flash-RL vs MiniCPM-V 4.7 35B-A3B
- MiniCPM-o 4.5 vs MiniCPM-V 4.7 1B
- MiniCPM-o 4.5 vs MiniCPM5-2B
- MiniCPM-o 4.5 vs MiniMax-M2.5
- MiniCPM-o 4.5 vs MiniMax-M2.7
- MiniCPM-o 4.5 vs MiniMax-M3.1-Flash
- MiniCPM-o 4.5 vs Mistral Large 4
- MiniCPM-o 4.5 vs Muse Glimmer 30B
- MiniCPM-o 4.5 vs Nanbeige4.2-3B
- MiniCPM-o 4.5 vs Nanbeige4.3-33B
- MiniCPM-o 4.5 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- MiniCPM-o 4.5 vs Nemotron 3.5 Lightning 30B A3B
- MiniCPM-o 4.5 vs Nemotron 3 Nano 30B A3B
- MiniCPM-o 4.5 vs Nemotron 3 Nano 4B
- MiniCPM-o 4.5 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniCPM-o 4.5 vs Nemotron 3 Super 120B A12B
- MiniCPM-o 4.5 vs Nemotron 3 Ultra 550B A55B
- MiniCPM-o 4.5 vs North Mini Code 1.0
- MiniCPM-o 4.5 vs occamy-1.0
- MiniCPM-o 4.5 vs Olmo 3 7B Think
- MiniCPM-o 4.5 vs Ornith-1.5-122B
- MiniCPM-o 4.5 vs Ornith-1.5-35B-A3B
- MiniCPM-o 4.5 vs Ornith-1.5-397B
- MiniCPM-o 4.5 vs Ornith-1.5-9B
- MiniCPM-o 4.5 vs OTel-2.0-LLM-31B-IT
- MiniCPM-o 4.5 vs Qwen-AgentWorld-35B-A3B
- MiniCPM-o 4.5 vs Qwen3-30B-A3B-Instruct-2507
- MiniCPM-o 4.5 vs Qwen3-4B-Instruct-2507
- MiniCPM-o 4.5 vs Qwen3.5-0.8B
- MiniCPM-o 4.5 vs Qwen3.5-122B-A10B
- MiniCPM-o 4.5 vs Qwen3.5-2B
- MiniCPM-o 4.5 vs Qwen3.5-397B-A17B
- MiniCPM-o 4.5 vs Qwen3.5-4B
- MiniCPM-o 4.5 vs Qwen3.5-9B
- MiniCPM-o 4.5 vs Qwen3.6-27B
- MiniCPM-o 4.5 vs Qwen3.6-35B-A3B
- MiniCPM-o 4.5 vs Qwen3.8-27B
- MiniCPM-o 4.5 vs Qwen3.8-Flash-Next
- MiniCPM-o 4.5 vs Qwen3-Coder-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-Coder-Next
- MiniCPM-o 4.5 vs Qwen3-Omni-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-2B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-32B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-4B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-8B-Instruct
- MiniCPM-o 4.5 vs Qwopus3.8-27B-Flash-V2
- MiniCPM-o 4.5 vs Recursive Flint
- MiniCPM-o 4.5 vs Ripple-65B Preview
- MiniCPM-o 4.5 vs SenseNova-Loop-9B-Preview
- MiniCPM-o 4.5 vs SmolLM3-3B
- MiniCPM-o 4.5 vs Spark-X2.6-4B
- MiniCPM-o 4.5 vs Step 3.7 Flash
- MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-27B
- MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-Flash-Next
- MiniCPM-o 4.5 vs ThinkingCap (Qwen3.8 27B)
- MiniCPM-o 4.5 vs Baidu Unlimited-OCR-2
- MiniCPM-o 4.5 vs WeVisOne-VL-2B
- MiniCPM-o 4.5 vs WeVisOne-VL-4B
- MiniCPM-o 4.5 vs ZAYA1-8B
- MiniCPM-V 4.7 1B vs MiniCPM-V 4.7 35B-A3B
- MiniCPM-V 4.7 35B-A3B vs MiniCPM5-2B
- MiniCPM-V 4.7 35B-A3B vs MiniMax-M2.5
- MiniCPM-V 4.7 35B-A3B vs MiniMax-M2.7
- MiniCPM-V 4.7 35B-A3B vs MiniMax-M3.1-Flash
- MiniCPM-V 4.7 35B-A3B vs Mistral Large 4
- MiniCPM-V 4.7 35B-A3B vs Muse Glimmer 30B
- MiniCPM-V 4.7 35B-A3B vs Nanbeige4.2-3B
- MiniCPM-V 4.7 35B-A3B vs Nanbeige4.3-33B
- MiniCPM-V 4.7 35B-A3B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3.5 Lightning 30B A3B
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3 Nano 30B A3B
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3 Nano 4B
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3 Super 120B A12B
- MiniCPM-V 4.7 35B-A3B vs Nemotron 3 Ultra 550B A55B
- MiniCPM-V 4.7 35B-A3B vs North Mini Code 1.0
- MiniCPM-V 4.7 35B-A3B vs occamy-1.0
- MiniCPM-V 4.7 35B-A3B vs Olmo 3 7B Think
- MiniCPM-V 4.7 35B-A3B vs Ornith-1.5-122B
- MiniCPM-V 4.7 35B-A3B vs Ornith-1.5-35B-A3B
- MiniCPM-V 4.7 35B-A3B vs Ornith-1.5-397B
- MiniCPM-V 4.7 35B-A3B vs Ornith-1.5-9B
- MiniCPM-V 4.7 35B-A3B vs OTel-2.0-LLM-31B-IT
- MiniCPM-V 4.7 35B-A3B vs Qwen-AgentWorld-35B-A3B
- MiniCPM-V 4.7 35B-A3B vs Qwen3-30B-A3B-Instruct-2507
- MiniCPM-V 4.7 35B-A3B vs Qwen3-4B-Instruct-2507
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-0.8B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-122B-A10B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-2B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-397B-A17B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-4B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5-9B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.6-27B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.6-35B-A3B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.8-27B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.8-Flash-Next
- MiniCPM-V 4.7 35B-A3B vs Qwen3-Coder-30B-A3B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-Coder-Next
- MiniCPM-V 4.7 35B-A3B vs Qwen3-Omni-30B-A3B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-VL-2B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-VL-30B-A3B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-VL-32B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-VL-4B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwen3-VL-8B-Instruct
- MiniCPM-V 4.7 35B-A3B vs Qwopus3.8-27B-Flash-V2
- MiniCPM-V 4.7 35B-A3B vs Recursive Flint
- MiniCPM-V 4.7 35B-A3B vs Ripple-65B Preview
- MiniCPM-V 4.7 35B-A3B vs SenseNova-Loop-9B-Preview
- MiniCPM-V 4.7 35B-A3B vs SmolLM3-3B
- MiniCPM-V 4.7 35B-A3B vs Spark-X2.6-4B
- MiniCPM-V 4.7 35B-A3B vs Step 3.7 Flash
- MiniCPM-V 4.7 35B-A3B vs Swift 1.5 Qwen3.8-27B
- MiniCPM-V 4.7 35B-A3B vs Swift 1.5 Qwen3.8-Flash-Next
- MiniCPM-V 4.7 35B-A3B vs ThinkingCap (Qwen3.8 27B)
- MiniCPM-V 4.7 35B-A3B vs Baidu Unlimited-OCR-2
- MiniCPM-V 4.7 35B-A3B vs WeVisOne-VL-2B
- MiniCPM-V 4.7 35B-A3B vs WeVisOne-VL-4B
- MiniCPM-V 4.7 35B-A3B vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/minicpm-o-4-5-vs-minicpm-v-4-7-35b-a3b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/minicpm-o-4-5.json·/api/v1/tools/minicpm-v-4-7-35b-a3b.json - From a terminal
anchor compare minicpm-o-4-5 minicpm-v-4-7-35b-a3b(the CLI) - Over MCP
compare_tools {"a": "minicpm-o-4-5", "b": "minicpm-v-4-7-35b-a3b"}at/mcp, no key