MiMo-V2.6-Flash-RL vs MiniMax-M2.5

MiMo-V2.6-Flash-RL 59

Model card 14, Intended use, the architecture, the parameters, the context and the languages (in the metadata) are on the card. Training data 5, A description of the training method with no data sources, sizes or cut-off. Last change 20, the last commits, on 28 October 2026, updated the card, 13 days before this check. Responsiveness 5, Of the 13 most recent discussions that aren't pull requests (21 September to 6 November 2026), 3 have a reply from a XiaomiMiMo member, which is a few. Version policy 5, MiMo-V2.5 stays in its own repositories and V2.6 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the 1M context, and two early faults (invalid JSON in the draft model's config, preprocessor values) were fixed in commits that say so. 14 + 5 + 20 + 5 + 5 + 10 = 59.

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.

MiMo-V2.6-Flash-RL 45

File safety 5, the weights are safetensors, but the dflash folder's mask_embedding.pt is a pickle beside them (15). Provenance 15, the files sit in the XiaomiMiMo organisation, which mimo.xiaomi.com links to per the Distill listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions only. Licence risk 15, MIT has no use policy, threshold or change clause. Security programme 5, Xiaomi runs a company security centre for reporting flaws, as read for the Distill listing (5). 5 + 15 + 0 + 5 + 15 + 5 = 45.

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.

MiMo-V2.6-Flash-RL 85

Chat template 20, chat_template.jinja in the repository (3,868 characters), with a copy in tokenizer_config.json. Tool-calling format 25, the card names the parser to use in two runtimes: the mimo tool-call parser in SGLang and in vLLM, with auto tool choice, and both ship it in a release. Trained tool calling 20, the card describes reinforcement learning on coding and general agent tasks across several harnesses, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, the template has an enable_thinking switch and keeps reasoning_content, and the card names the mimo reasoning parser for SGLang and vLLM, which returns the reasoning apart from the answer. Context 10, 1M tokens per the card's model summary, and 1,048,576 positions in 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.