BenchmarksMiniMaxToday
MiniMax-M2.1 Benchmark Update
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
View sourceMiniMax
MiniMax coding and reasoning model optimized for real-world programming, workplace tasks, and agentic software workflows.
26.1
Quality Score
---
Arena ELO
Undisclosed
Parameters
1M
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
17 of 22 public signals
Sign in to join the discussion
0
Downloads
0
Likes
Dec 2025
Released
4/5 signals
3/4 signals
5/5 signals
1/4 signals
4/4 signals
Parameters
229B
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: Open weights (restricted use) · Confident confidence
Gaps we are still tracking
Benchmarks
20
Open Source
1
General
3
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
View sourceQuality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
View sourceQuality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
View sourceQuality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
View sourceQuality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
Quality: 32.1/100 | Price: $0.525/M tokens | Output: 0 tok/s | MMLU: 0.875% | HumanEval: 0.81%
MiniMax says the M2 family is open-sourced with official self-host guidance for private deployment using runtimes like vLLM and SGLang.
MiniMax 开源新评测集：定义Coding Agent 的生产级标准 - MiniMax News | MiniMax 模型 语言模型 MiniMax M3 MiniMax M2.7 MiniMax M2.5 视频生成 MiniMax H3 语音&音乐 MiniMax Speech 2.8 MiniMax Music 3.0 产品 MiniMax Code MiniMax Design 语音 星野 API Token Plan 研究 关于我们 与所有人共创智能 公司介绍 新闻 投资者关系 加入我们 EN 模型 语言模型 MiniMax M3 NEW MiniMax M2.7 MiniMax M2.5 视频生成 MiniMax H3 NEW 语音&音乐 MiniMax Speech 2.8 NEW MiniMax Music 3.0 NEW 产品 MiniMax Code NEW MiniMax Design 语音 星野 API Token Plan 研究 关于我们 与所有人共创智能 公司介绍 新闻 投资者关系 加入我们 Eng