Quality
Highest overall scores
- 1
MiniMax: MiniMax M345.4 - 2MiniMax: MiniMax M2.738.9
- 3MiniMax: MiniMax M2.50
MiniMax model benchmarks.
Compare MiniMax models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1MiniMax: MiniMax M2.7279 t/s
- 2MiniMax: MiniMax M2.5101 t/s
- 3MiniMax: MiniMax M391 t/s
Input price
Lowest price per 1M tokens
- 1MiniMax: MiniMax M2.5$0.22/1M
- 2MiniMax: MiniMax M3$0.30/1M
- 3MiniMax: MiniMax M2.7$0.30/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare MiniMax model capability.
Performance and price
Compare practical tradeoffs.
All MiniMax models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| MiniMax: MiniMax M3 | 45.4 | 91 t/s | 1M | $0.30 | $1.20 | |
| MiniMax: MiniMax M2.7 | 38.9 | 279 t/s | 204.8K | $0.30 | $1.20 | |
| MiniMax: MiniMax M2.5 | 0 | 101 t/s | 204.8K | $0.22 | $0.90 |
MiniMax technical benchmarks.
Compare named evaluation records available for MiniMax models. Missing results remain blank rather than being estimated.
| Benchmark | Area | MiniMax M3 | MiniMax M2.7 | MiniMax M2.5 | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 45.4 | 38.9 | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 58.6 | 52.6 | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 36.1 | 25.9 | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 92.9 | 87.4 | 84.8 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 39 | 29.6 | 20.5 | OpenRouter model benchmarks |
| IFBench | IFBench | 82.9 | 75.7 | 71.6 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 88.9 | 84.8 | 95.3 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 80.3 | 75.3 | 72 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 44.4 | 33 | — | OpenRouter model benchmarks |
| CritPt | CritPt | 3.7 | 0.6 | 1.1 | OpenRouter model benchmarks |
| SciCode | SciCode | 45.4 | 47 | 42.6 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 42.4 | 39.4 | 34.8 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 16.7 | 26.8 | 26.2 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 81.6 | 64.4 | 11.9 | OpenRouter model benchmarks |
| SWE-bench Pro | Coding | — | — | 55.4 | OpenEvals/leaderboard-data |
| SWE-bench Verified | Coding | — | — | 75.8 | OpenEvals/leaderboard-data |
MiniMax video models.
| Model | Quality | Text to video | Image to video | Links |
|---|---|---|---|---|
| H3 | — | — | — | View details |
| Hailuo 2.3 | — | — | — | View details |