Sign in

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

Mistral Large 4 vs Ripple-65B Preview

Mistral Large 4 scores 54.6 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), 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 3674 open weights comparisons

Mistral Large 4Mistral AI · Open-weight model C54.6/100#97 of 121 open-weight models Ripple-65B PreviewRicursive Intelligence · Open-weight model D53.3/100#103 of 121 open-weight models

Which one, for what

Mistral Large 4 C

Best for Operators with an 8-GPU Blackwell or H200 node who want a frontier-sized open model for coding agents and defensive security, with a hosted twin on Mistral's API.

Ahead on

  • Reach, 50 against 45
  • Risk, 75 against 55
  • Agent interface, 95 against 75
  • Documentation and upkeep, 64 against 49

Watch for

The smallest 4-bit build needs about 732 GB, so nothing fits a single workstation or a 128 GB machine

Ripple-65B Preview D

Best for Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code

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.

Risk Mistral Large 4 +20

Mistral Large 4 75

File safety scores 25, safetensors only and loaded by Transformers' own code with a Jinja template. Provenance scores 15, Mistral's verified organisation with a hash on every file. Safety evaluation scores 10, refusal and prompt-injection results Mistral ran itself, listed in its 2 November technical report as internal, and red-teaming by outside firms with nothing published. Agent guidance scores 10 for a statement of what the refusals cover and a claim of trained injection resistance, with only general safeguards. Licence risk scores 10, 5 off for the Model-as-a-Service limit. The security programme scores 5 for security.txt with no public advisories. 25 + 15 + 10 + 10 + 10 + 5 = 75.

Ripple-65B Preview 55

File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.

Agent interface Mistral Large 4 +20

Mistral Large 4 95

The chat template is in the repository (20). The card documents how tools are declared and come back and names the parser (25), and the template renders several calls in one turn (20). Strict JSON Schema output is documented with how to ask for it (15). Reasoning effort is budgeted per request with the reasoning returned apart from the answer (10). Context scores 5, because the 1M window comes from YaRN scaling and the technical report gives 40K as the longest pretraining sequence. 20 + 25 + 20 + 15 + 10 + 5 = 95.

Ripple-65B Preview 75

Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M.

Documentation and upkeep Mistral Large 4 +15

Mistral Large 4 64

The card covers intended use, architecture, parameters, context and languages, and misses limitations and a cut-off (14). Training data is described by its mix in the technical report, with no sources, cut-off or filtering (5). The files changed on 2 November 2026, when the report was added (20). A Mistral member replied in three of nine discussions (10). It's a first release with older Large models in their own repositories and no dated note (5), and the files agree with each other and the card (10). 14 + 5 + 20 + 10 + 5 + 10 = 64.

Ripple-65B Preview 49

Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M.

Reach Mistral Large 4 +5

Mistral Large 4 50

Memory scores 0, since the smallest 4-bit build, Mistral's NVFP4, is 610 GB, about 732 GB with a fifth added, far above 256 GB. Runtimes score 10, released Transformers and llama.cpp have the architecture, while vLLM v0.33.0 and SGLang v0.5.23 still lack it, the llama.cpp build Ollama 0.40.14 pins predates it, and LM Studio has no entry. Builds score 15 for Mistral's FP8 and NVFP4 releases. Terms score 10, a modified MIT licence that is free commercially except for Model-as-a-Service businesses. Download scores 10 with no gate, and hosted too scores 5 because Mistral's API serves these weights. 0 + 10 + 15 + 10 + 10 + 5 = 50.

Ripple-65B Preview 45

Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.

Score by category

CategoryWeight this runMistral Large 4Ripple-65B PreviewEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255045Mistral Large 4 +5
Risk20%207555Mistral Large 4 +20
Agent interface10%109575Mistral Large 4 +20
Documentation and upkeep10%106449Mistral Large 4 +15
Negative events≤1500
TotalC 54.6/100D 53.3/100

Facts side by side

FactMistral Large 4Ripple-65B Preview
KindOpen-weight modelOpen-weight model
VendorMistral AIRicursive Intelligence
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMistral Ecosystem Open-Weight License (modified MIT)Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-292026-11-04
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked

Verdicts

Mistral Large 4

A 1T-parameter mixture-of-experts model from Mistral for coding agents and defensive security, with strict JSON Schema output, parallel tool calls and three reasoning efforts. It needs a multi-GPU server, about 732 GB for the smallest 4-bit build, and no released vLLM or SGLang loads it. The licence bars Model-as-a-Service businesses without a separate deal.

Ripple-65B Preview

A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.

Before you call either

Mistral Large 4

  1. Serve the NVFP4 build on Blackwell with vllm/vllm-openai:mistral-large-4 --model mistralai/Mistral-Large-4-1T-A52B-NVFP4 --tensor-parallel-size 8 --kv-cache-dtype fp8_ds_mla --tool-call-parser mistral --reasoning-parser mistral --enable-auto-tool-choice; released vLLM doesn't load it
  2. On H200 use the FP8 build with tensor parallelism of 16 or 8 by 2 pipelines, per vLLM's recipe
  3. Pass reasoning_effort low, medium or high (default high); any other value makes the template raise an error, and there is no off switch
  4. Read the reasoning from message.reasoning; max_completion_tokens counts reasoning tokens too
  5. Use temperature 1.0 and top_p 0.95 at every effort, per the card
  6. Ask for JSON with response_format type json_schema and strict true; the template passes the schema to the model
  7. The template rejects a tool message straight after a user message and a conversation that doesn't start with a user or system message
  8. Add --speculative-config '{"method": "dspark", "num_speculative_tokens": 3}' to use the embedded draft head
  9. If you'll offer it to others as a hosted model, read the licence first; Model-as-a-Service use needs Mistral's commercial licence

Ripple-65B Preview

  1. Run Ricursive's launcher from inference/server with uv run --script serve.py on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default
  2. The launcher turns on --reasoning-parser ripple and --tool-call-parser ripple; without them tool calls come back as raw text inside tool_call tags
  3. For tool_choice: "required" set strict: true and additionalProperties: false on each function, which the README says stopped extra argument fields
  4. Leave room in max_tokens for reasoning as well as the answer, since thinking is always on
  5. Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support

Questions

Which is better for AI agents, Mistral Large 4 or Ripple-65B Preview?

Mistral Large 4 scores 54.6 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in every scored category.

Other comparisons with Mistral Large 4 or Ripple-65B Preview

Machine-readable

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 auditSee a sample report