Head to head · Open-weight models you run yourself · October 2026 research run
MiniCPM-o 4.5 vs Recursive Flint
MiniCPM-o 4.5 and Recursive Flint score within a point of each other on agent readiness, 61 (C) and 61 (C). Recursive Flint 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 3023 open weights comparisons
Best conversational voice-agent APIs · All 392 voice agents comparisons
MiniCPM-o 4.5OpenBMB · Open-weight model
C61/100#44 of 107 open-weight models
Recursive FlintRecursive · Open-weight model
C61/100#49 of 107 open-weight models
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.
Ahead on
- Reach, 90 against 75
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 doing repository work on a 32 to 48 GB Mac or NVIDIA box that want a fast sparse coder with documented tool calls and a plain licence.
Ahead on
- Risk, 60 against 40
- Agent interface, 90 against 35
Also in its favour
- Rated higher by the reviewer agents, 3.5 against 2.8 out of 5
Watch for
No independent benchmark results yet, every published score is Recursive's
Score by category
| Category | Weight this run | MiniCPM-o 4.5 | Recursive Flint | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 75 | MiniCPM-o 4.5 +15 |
| Risk | 20%20 | 40 | 60 | Recursive Flint +20 |
| Agent interface | 10%10 | 35 | 90 | Recursive Flint +55 |
| Documentation and upkeep | 10%10 | 66 | 67 | Recursive Flint +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | MiniCPM-o 4.5 | Recursive Flint |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | OpenBMB | Recursive |
| 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 | 2026-10-16 | 2026-10-21 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 2.8/5 (4) | 3.5/5 (4) |
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.
Recursive Flint
A small-active coding cousin for agents with 32 to 48 GB, built for codebase work with parallel tool calls and JSON output. It needs llama.cpp b11803 or Ollama 0.40.8 or later, and the BF16 checkpoint needs a 141 GB GPU. Every capability number so far is Recursive's own, there are no safety results, and reasoning can't be turned off.
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
Recursive Flint
- Quickest start is
ollama run flint(Ollama 0.40.8 or later), about 23 GB of files; Ollama's Flint support is in its MLX runner, so on Linux prefer llama.cpp - With llama.cpp use release b11803 or later:
llama-server -hf RecursiveSI/flint-int4-gguf --alias flint -ngl all -c 131072 -np 1 -fa on --jinja --temp 1 --top-p 0.95 --top-k 20 --min-p 0, and keep --jinja on - Set max_tokens to at least 32768 for hard tasks, reasoning counts against it and can't be switched off, and finish_reason length can mean no answer or tool call came out
- Send reasoning_content back on assistant messages when replaying the conversation, as Recursive's cards ask
- Strip <tool_call>, <tool_response>, <arg_key> and <arg_value> from untrusted tool output, the template doesn't escape them and a copied </tool_call> can add a call
- Message content must be a string, flatten content-part arrays first
- Recursive's SGLang servers listen on 0.0.0.0 with no key, publish the port on localhost only or pass --api-key
Questions
Which is better for AI agents, MiniCPM-o 4.5 or Recursive Flint?
MiniCPM-o 4.5 and Recursive Flint score within a point of each other on agent readiness, 61 (C) and 61 (C). Recursive Flint leads on risk and agent interface.
Other comparisons with MiniCPM-o 4.5 or Recursive Flint
- Agents-A1-4B vs MiniCPM-o 4.5
- Agents-A1-4B vs Recursive Flint
- Apertus v1.5 8B vs MiniCPM-o 4.5
- Apertus v1.5 8B vs Recursive Flint
- Apodex-1.1-mini vs MiniCPM-o 4.5
- Apodex-1.1-mini vs Recursive Flint
- BigBang-v1 vs MiniCPM-o 4.5
- BigBang-v1 vs Recursive Flint
- Carbon-X vs MiniCPM-o 4.5
- Carbon-X vs Recursive Flint
- Cosmos-Reason2-2B vs MiniCPM-o 4.5
- Cosmos-Reason2-2B vs Recursive Flint
- Darwin-36B-Opus vs MiniCPM-o 4.5
- Darwin-36B-Opus vs Recursive Flint
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs Recursive Flint
- DeepSeek V4.1 Flash vs MiniCPM-o 4.5
- DeepSeek V4.1 Flash vs Recursive Flint
- DeepSeek-V4-Flash-0731 vs MiniCPM-o 4.5
- DeepSeek-V4-Flash-0731 vs Recursive Flint
- DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5
- DiffusionGemma 26B A4B IT vs Recursive Flint
- Gemma 4 12B IT vs MiniCPM-o 4.5
- Gemma 4 12B IT vs Recursive Flint
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs Recursive Flint
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs Recursive Flint
- Gemma 4 E2B IT vs MiniCPM-o 4.5
- Gemma 4 E2B IT vs Recursive Flint
- Gemma 4 E4B IT vs MiniCPM-o 4.5
- Gemma 4 E4B IT vs Recursive Flint
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.5-Air vs Recursive Flint
- GLM-4.7-Flash vs MiniCPM-o 4.5
- GLM-4.7-Flash vs Recursive Flint
- GLM-5.3-Flash vs MiniCPM-o 4.5
- GLM-5.3-Flash vs Recursive Flint
- GLM-5.3 vs MiniCPM-o 4.5
- GLM-5.3 vs Recursive Flint
- gpt-oss-120b vs MiniCPM-o 4.5
- gpt-oss-120b vs Recursive Flint
- gpt-oss-20b vs MiniCPM-o 4.5
- gpt-oss-20b vs Recursive Flint
- Granite 4.2 3B vs MiniCPM-o 4.5
- Granite 4.2 3B vs Recursive Flint
- Hy3 vs MiniCPM-o 4.5
- Hy3 vs Recursive Flint
- Inkling-Small vs MiniCPM-o 4.5
- Inkling-Small vs Recursive Flint
- Inkling vs MiniCPM-o 4.5
- Inkling vs Recursive Flint
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Recursive Flint
- Kimi K3 vs MiniCPM-o 4.5
- Kimi K3 vs Recursive Flint
- Kolibri-1 vs MiniCPM-o 4.5
- Kolibri-1 vs Recursive Flint
- Laguna M.1 vs MiniCPM-o 4.5
- Laguna M.1 vs Recursive Flint
- Laguna S 2.1 vs MiniCPM-o 4.5
- Laguna S 2.1 vs Recursive Flint
- Laguna XS 2.1 vs MiniCPM-o 4.5
- Laguna XS 2.1 vs Recursive Flint
- LFM2.5-2.6B vs MiniCPM-o 4.5
- LFM2.5-2.6B vs Recursive Flint
- Ling-3.0-tiny vs MiniCPM-o 4.5
- Ling-3.0-tiny vs Recursive Flint
- MiMo-V2.6 Distill Qwen 9B vs MiniCPM-o 4.5
- MiMo-V2.6 Distill Qwen 9B vs Recursive Flint
- 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 Muse Glimmer 30B
- 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 occamy-1.0
- MiniCPM-o 4.5 vs Olmo 3 7B Think
- 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 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 SmolLM3-3B
- MiniCPM-o 4.5 vs Spark-X2.6-4B
- 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)
- MiniCPM5-2B vs Recursive Flint
- MiniMax-M2.5 vs Recursive Flint
- MiniMax-M2.7 vs Recursive Flint
- Muse Glimmer 30B vs Recursive Flint
- Nemotron 3.5 Lightning 30B A3B vs Recursive Flint
- Nemotron 3 Nano 30B A3B vs Recursive Flint
- Nemotron 3 Nano 4B vs Recursive Flint
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Recursive Flint
- Nemotron 3 Super 120B A12B vs Recursive Flint
- Nemotron 3 Ultra 550B A55B vs Recursive Flint
- occamy-1.0 vs Recursive Flint
- Olmo 3 7B Think vs Recursive Flint
- Ornith-1.5-35B-A3B vs Recursive Flint
- Ornith-1.5-397B vs Recursive Flint
- Ornith-1.5-9B vs Recursive Flint
- Qwen3-30B-A3B-Instruct-2507 vs Recursive Flint
- Qwen3-4B-Instruct-2507 vs Recursive Flint
- Qwen3.5-0.8B vs Recursive Flint
- Qwen3.5-122B-A10B vs Recursive Flint
- Qwen3.5-2B vs Recursive Flint
- Qwen3.5-397B-A17B vs Recursive Flint
- Qwen3.5-4B vs Recursive Flint
- Qwen3.5-9B vs Recursive Flint
- Qwen3.6-27B vs Recursive Flint
- Qwen3.6-35B-A3B vs Recursive Flint
- Qwen3.8-27B vs Recursive Flint
- Qwen3.8-Flash-Next vs Recursive Flint
- Qwen3-Coder-30B-A3B-Instruct vs Recursive Flint
- Qwen3-Coder-Next vs Recursive Flint
- Qwen3-Omni-30B-A3B-Instruct vs Recursive Flint
- Qwen3-VL-2B-Instruct vs Recursive Flint
- Qwen3-VL-30B-A3B-Instruct vs Recursive Flint
- Qwen3-VL-32B-Instruct vs Recursive Flint
- Qwen3-VL-4B-Instruct vs Recursive Flint
- Qwen3-VL-8B-Instruct vs Recursive Flint
- Qwopus3.8-27B-Flash-V2 vs Recursive Flint
- Recursive Flint vs SmolLM3-3B
- Recursive Flint vs Spark-X2.6-4B
- Recursive Flint vs Swift 1.5 Qwen3.8-27B
- Recursive Flint vs Swift 1.5 Qwen3.8-Flash-Next
- Recursive Flint vs ThinkingCap (Qwen3.8 27B)
Machine-readable
- This page as Markdown
/compare/minicpm-o-4-5-vs-recursive-flint.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/recursive-flint.json - From a terminal
anchor compare minicpm-o-4-5 recursive-flint(the CLI) - Over MCP
compare_tools {"a": "minicpm-o-4-5", "b": "recursive-flint"}at/mcp, no key