MiniMax, open weights
MiniMax-M2.1
MiniMax-M2.1 by MiniMax ranks 178th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.9. Its strongest category is agentic & tool use, where it ranks 98th. API pricing starts at $0.30 per million input tokens and $1.20 per million output tokens, with a 205K-token context window.
Last verified
Specifications
- Noometry rank
- #178 of 354
- Index score
- 38.9
- Evidence
- Confirmed 22 results
- Provider
MiniMax- Released
- December 23, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 205K
- Max output
- 131K
- Input price
- $0.30 / M
- Output price
- $1.20 / M
- Blended price
- $0.52 / M
- Output speed
- Not measured
- Value
- #78 of 219
- Knowledge cutoff
- Unknown
- Input
- text
- Hugging Face
- MiniMaxAI/MiniMax-M2.1
Category scores
Each category score combines every public result we have in that category.
- Coding 40.4
- Agentic & Tool Use 27.9
- Reasoning 16.6
- Math 38.3
- Knowledge 38.3
- Multilingual 50.0
- Instruction Following 73.8
- Long Context 43.2
- Writing & Preference 58.3
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.4 | #143 | 2 |
| Agentic & Tool Use | 27.9 | #98 | 1 |
| Reasoning | 16.6 | #302 | 2 |
| Math | 38.3 | #138 | 1 |
| Knowledge | 38.3 | #147 | 2 |
| Multilingual | 50.0 | #128 | 1 |
| Instruction Following | 73.8 | #112 | 1 |
| Long Context | 43.2 | #101 | 1 |
| Writing & Preference | 58.3 | #120 | 3 |
Strengths and weaknesses
Categories where MiniMax-M2.1 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Long Context | 43.2 | +2.3 | #101 of 296, top 35% |
| Instruction Following | 73.8 | +2.6 | #112 of 305, top 37% |
| Writing & Preference | 58.3 | +4.5 | #120 of 312, top 39% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 16.6 | −7.0 | #302 of 350, top 87% |
| Agentic & Tool Use | 27.9 | −2.5 | #98 of 154, top 64% |
| Knowledge | 38.3 | +1.0 | #147 of 314, top 47% |
Closest competitors
The models ranked just above and below MiniMax-M2.1. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Molmo 2 8b | #174 | 39.1 | — | — | Compare |
| Mercury 2 | #175 | 39.1 | $0.38 | — | Compare |
| Mistral Large 3 | #176 | 39.1 | $0.38 | 7 | Compare |
| GLM-4.5-Air | #177 | 38.9 | $0.43 | 160 | Compare |
| Qwen3-30B-A3B | #179 | 38.9 | $0.21 | 42 | Compare |
| GLM-4.7-Flash | #180 | 38.8 | $0.15 | — | Compare |
| Qwen2.5 Plus 1127 | #181 | 38.8 | — | — | Compare |
| Qwen3.6 Flash | #182 | 38.8 | $0.42 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1384 | #79 of 113, top 70% | LMArena | 2026-10-08 | |
| LMArena Coding | 1421 | #117 of 294, top 40% | LMArena | 2026-10-08 | |
| ALE-Bench | 623.83 | #77 of 105, top 74% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | 36.6% | #26 of 41, top 64% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| NYT Connections (extended) | 11.2% | #86 of 91, top 95% | Lech Mazur benchmarks | ||
| LMArena Hard Prompts | 1411 | #118 of 297, top 40% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1397 | #128 of 285, top 45% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 11.8% | #71 of 96, top 74% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1431 | #97 of 273, top 36% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1378 | #128 of 297, top 44% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1430 | #119 of 285, top 42% | LMArena | 2026-10-08 | |
| LMArena French | 1404 | #116 of 223, top 53% | LMArena | 2026-10-08 | |
| LMArena German | 1381 | #109 of 231, top 48% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1287 | #128 of 211, top 61% | LMArena | 2026-10-08 | |
| LMArena Korean | 1298 | #132 of 213, top 62% | LMArena | 2026-10-08 | |
| LMArena Russian | 1387 | #123 of 283, top 44% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1397 | #114 of 226, top 51% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1400 | #105 of 298, top 36% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1416 | #96 of 291, top 33% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1392 | #127 of 297, top 43% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1361 | #120 of 295, top 41% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1396 | #122 of 295, top 42% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.30 | $1.20 | — | 2026-10-10 |
| minimax | $0.30 | $1.20 | $0.03 | 2026-10-10 |
| openrouter | $0.30 | $1.20 | $0.03 | 2026-10-10 |
Compare MiniMax-M2.1
- MiniMax-M2.1 vs MiniMax-M2
- MiniMax-M2.1 vs GLM-4.5-Air
- MiniMax-M2.1 vs Qwen3-30B-A3B
- MiniMax-M2.1 vs Mistral Large 3
- MiniMax-M2.1 vs GLM-4.7-Flash
- MiniMax-M2.1 vs Mercury 2
- MiniMax-M2.1 vs Qwen2.5 Plus 1127
- MiniMax-M2.1 vs GPT-6 Astra
- MiniMax-M2.1 vs Claude Fable 5.1
- MiniMax-M2.1 vs Gemini 3.8 Flash
- MiniMax-M2.1 vs Kimi K3
- MiniMax-M2.1 vs Grok 4.6
- MiniMax-M2.1 vs Qwen3.8 Max
- MiniMax-M2.1 vs GLM-5.3
Other MiniMax models
Frequently asked questions
How good is MiniMax-M2.1?
MiniMax-M2.1 by MiniMax ranks 178th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.9. Its strongest category is agentic & tool use, where it ranks 98th. API pricing starts at $0.30 per million input tokens and $1.20 per million output tokens, with a 205K-token context window.
How much does MiniMax-M2.1 cost?
MiniMax-M2.1 costs $0.30 per million input tokens and $1.20 per million output tokens on MiniMax's own API, with cached input at $0.03.
What is MiniMax-M2.1's context window?
MiniMax-M2.1 accepts up to 205K tokens of input and can write up to 131K tokens in one response.
Is MiniMax-M2.1 open source?
Yes. MiniMax-M2.1's weights are downloadable from Hugging Face (MiniMaxAI/MiniMax-M2.1); check the license for commercial terms.
What are MiniMax-M2.1's strengths and weaknesses?
Relative to other ranked models, MiniMax-M2.1 places best in long context, instruction following, writing & preference and lowest in reasoning, agentic & tool use, knowledge.
What is MiniMax-M2.1 best at?
Its best category is agentic & tool use, where it ranks 98th on Noometry.