LLM Comparison

MiniMax M2.5 vs MiniMind

Side-by-side specs, pricing & capabilities · Updated October 2026

Add to comparison

2/6 models
Same tier:
 MiniMaxMiniMax M2.5Jingyao GongMiniMind
OrganizationMiniMaxMiniMaxJingyao GongJingyao Gong
OpenTools Score
48
FamilyMiniMaxMiniMind
StatusCurrentCurrent
Release DateFeb 2026Sep 2026
Context Window197K tokens1K tokens
Input Price——
Output Price——
Pricing NotesFree tier available on OpenRouter with rate limitsOpen-source project; API pricing is not applicable unless a downstream host adds serving costs.
Capabilities
textcode
texteducationtraining
Training Cutoff—Not specified
Max Output8K tokens1K tokens
API Identifierminimax/minimax-m2.5:freejingyaogong/minimind
Benchmarks
GPQA Diamond
84.8485artificial-analysis
—
 View MiniMax M2.5View MiniMind

MiniMax

MiniMax M2.5

MiniMax M2.5 is a large language model from MiniMax. Supports up to 196,608 token context window. Available free with rate limits on OpenRouter.

Jingyao Gong

MiniMind

MiniMind is a small open-source language-model training project that demonstrates how to train a 64M-parameter LLM from scratch. The repository is aimed at builders who want a compact, inspectable model-training path rather than a hosted frontier API.

More Comparisons

Flagship

GPT-6.1 Sol vs Claude Sonnet 5.5

Flagship

GPT-6.1 Sol vs Grok 4.7

Flagship

GPT-6.1 Sol vs Gemini 3.6 Flash

Flagship

GPT-6.1 Sol vs Palmyra X5

Flagship

GPT-6.1 Sol vs Jamba Large 1.7

Flagship

GPT-6.1 Sol vs Command A

Looking for more AI models?

Browse All LLMs