MiniMax M1 80k
Jun 2025
MiniMax M1 80kCompare inon
Benchmarks of MiniMax M1 80k13
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen×4-44%$0.13Memory (4-bit): 274 GB → 615 GB+4
BetterGPT-6 Lunalow+84%-79%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×3.8-45%$0.26Memory (4-bit): 274 GB → 458 GB+5
CheaperClaude Haiku 5.5max×3.7-79%$0.21Remove sampling parameters+5CheaperMiniMax M3.1 Flashthinking×3.6-73%$0.22Complete model response must be appendedModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×4-44%$0.13Memory (4-bit): 274 GB → 615 GB+4DeepSeek V4.1 Flash 1017maxOpen×3.8-45%$0.26Memory (4-bit): 274 GB → 458 GB+5Claude Haiku 5.5max×3.7-79%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking×3.6-73%$0.22Complete model response must be appended
GLM 5.3 FlashmaxOpen×3.6-75%$0.28Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+84%-79%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+79%-53%$0.01MiMo v2.5thinkingOpen+86%-82%$0.019Claude Haiku 5.5low×2.5-79%$0.024Remove sampling parameters+5GPT-5 Minihigh+43%-29%$0.053Context: 1M → 400KModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×4-44%$0.13Memory (4-bit): 274 GB → 615 GB+4DeepSeek V4.1 Flash 1017maxOpen×3.8-45%$0.26Memory (4-bit): 274 GB → 458 GB+5GLM 5.3maxOpen×3.8+123%$2.01Memory (4-bit): 274 GB → 452 GB+4
Step 5 PreviewthinkingOpen×3.7+48%$1.03Memory (4-bit): 274 GB → 363 GB+3GLM 5.3 FlashmaxOpen×3.6-75%$0.28Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
MiniMax M3.1 Flashthinking×3.6—$0.22Complete model response must be appendedMiniMax M3thinkingOpen×2.5—$0.51Context: 1M → 524K+2MiniMax M2.5thinkingOpen+94%—$0.30 / $1.20Context: 1M → 205KMiniMax M2.7thinkingOpen+94%—$0.30 / $1.20Context: 1M → 205KMiniMax M2.1thinkingOpen+79%—$0.30 / $1.20Context: 1M → 205KMiniMax M2thinkingOpen+59%—$0.30 / $1.20Context: 1M → 205KMiniMax M1 40kOpen-15%——MiniMax M1unstatedOpenn/a—$0.40 / $2.20No strict JSONAll MiniMax models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✗ 80 GB GPU
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam8.9#206
AA Omniscience Index-48.5#202
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈11.7#186
AA Omniscience · Accuracy22.5#134
AA-LCR (long context) 1.157.7#162
GPQA Diamond69.7#187
Coding
LiveCodeBench · AA archived71.1#42
Agents & Tool Use
τ²-bench · AA34.2#141
Writing & Language
IFBench (instructions)41.8#147
FAQ
How much does MiniMax M1 80k cost?›
$0.55 per 1M input tokens and $2.20 per 1M output tokens (cheapest host: Novita).
Is MiniMax M1 80k free to use?›
There is no free API; the cheapest paid price is $0.55 per 1M input tokens. The weights are open, so you can run it yourself.
How good is MiniMax M1 80k, and what is it best at?›
#205 of 334 in Chat & Knowledge, #177 of 239 in Coding, #139 of 242 in Agents & Tool Use, #146 of 245 in Writing & Language.
Is MiniMax M1 80k better than HyperNova 60B 2605?›
On AA Intelligence Index 4.3.2, MiniMax M1 80k scores 11.7 vs 11.7 — about the same.
How can I use MiniMax M1 80k?›
Through the API of Novita.
What is the context window of MiniMax M1 80k?›
1M tokens.
When was MiniMax M1 80k released? Is there a newer version?›
Released 2025-06-17. It has been superseded by MiniMax M2.
Is MiniMax M1 80k open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run MiniMax M1 80k locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can MiniMax M1 80k read images?›
No, it accepts text only.
What is MiniMax M1 80k?›
MiniMax M1 80k is an open-weights language model from MiniMax, released Jun 2025.
What are the best alternatives to MiniMax M1 80k?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).