MiniMax
MiniMax-M3
Quality Score46.4
Value Score40.2
Reliability50.7
Cache Discount80%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, video
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.300
- Output
- $1.20
- Cached Input
- $0.060
- Cached Output
- $0.375
- Cost per task
- $0.139
Capability
- Intelligence
- 45.4
- Coding
- 58.6
- Agentic
- 36.1
- Omniscience
- 1.4
- Correct
- 16.7%
- Blended price
- $0.222
Answer outcomes
Correct 16.7%Incorrect 15.3%Abstained 68.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 44%
- τ³-Banking
- 15%
- Terminal-Bench v2.1
- 65%
- SciCode
- 45%
- Humanity’s Last Exam
- 39%
- GPQA Diamond
- 93%
- CritPt
- 4%
- AA-Omniscience
- 51%
- AA-LCR
- 80%
Similar models
- MiMo-V2.5-ProXiaomiQuality Score 47.1Value Score 40.9
- Inkling SmallThinking MachinesQuality Score 46.0Value Score 41.1
- GPT-5.6 Luna (medium)OpenAIQuality Score 46.4Value Score 42.0
- Hy3TencentQuality Score 44.0Value Score 44.2
- Kimi K2.7 CodeKimiQuality Score 49.2Value Score 38.4
- Solar Pro 4UpstageQuality Score 43.9Value Score 37.9