readable AI benchmarks (simplified)
MiniMax
MiniMax-M3
MiniMax-M3 has a Quality Score of 47.8, ranking 123rd among 572 scored models. Per 1M tokens, pricing is $0.300 input, $1.20 output, $0.060 cached input, and $0.375 cache write. It accepts text, image, and video input, outputs text, and has a 1M token context window. Its Reliability Score is 50.7, ranking 117th among 574 scored models, above average (total average: 36.5). Its Value Score is 39.9, high compared with the total Value average of 31.5.
Quality Score47.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score39.9
Factual 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
- Cache write
- $0.375
- Cost per task
- $0.508
Capability
- Intelligence
- 29.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- 1.4
- Correct
- 16.7%
- Blended price
- $0.222
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 32.0%
Correct 16.7%Incorrect 15.3%Partial / not attempted 68.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 37%
- τ³-Banking
- 15%
- SciCode
- 47%
- Humanity’s Last Exam
- 39%
- GPQA Diamond
- 93%
- CritPt
- 4%
- AA-Omniscience
- 51%
- AA-LCR
- 83%
Similar models
- MiniMax-M2.7MiniMaxQuality Score 42.7Value Score 35.6
- MiniMax-M2.5MiniMaxQuality Score 32.8Value Score 27.6
- MiniMax-M2.1MiniMaxQuality Score 32.9Value Score 27.7
- MiniMax-M2MiniMaxQuality Score 27.7Value Score not available
- MiniMax M1 80kMiniMaxQuality Score 21.9Value Score not available
- MiniMax M1 40kMiniMaxQuality Score not availableValue Score not available