Quality
Highest overall scores
- 1
MiniMax: MiniMax M344.4 - 2MiniMax: MiniMax M2.738.1
- 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 M2.7294.5 t/s
- 2MiniMax: MiniMax M2.595 t/s
- 3MiniMax: MiniMax M383 t/s
Input price
Lowest price per 1M tokens
- 1MiniMax: MiniMax M2.5$0.15/1M
- 2MiniMax: MiniMax M2.7$0.25/1M
- 3MiniMax: MiniMax M3$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 | 44.4 | 83 t/s | 1M | $0.30 | $1.20 | |
| MiniMax: MiniMax M2.7 | 38.1 | 294.5 t/s | 204.8K | $0.25 | $1.00 | |
| MiniMax: MiniMax M2.5 | 0 | 95 t/s | 204.8K | $0.15 | $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 | 44.4 | 38.1 | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 58.6 | 52.6 | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 35.4 | 25.6 | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 92.9 | 87.4 | 85.2 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 37.1 | 28.1 | 19.4 | OpenRouter model benchmarks |
| IFBench | IFBench | 82.9 | 75.7 | — | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 88.9 | 84.8 | — | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 74 | 68.7 | — | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 44.5 | 32.9 | — | OpenRouter model benchmarks |
| CritPt | CritPt | 3.7 | 0.6 | — | OpenRouter model benchmarks |
| SciCode | SciCode | 45.4 | 47 | — | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 42.4 | 39.4 | — | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 15 | 26.1 | — | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 83.9 | 65.6 | — | OpenRouter model benchmarks |
| SWE-bench Pro | Coding | — | — | 55.4 | OpenEvals/leaderboard-data |
| SWE-bench Verified | Coding | — | — | 75.8 | OpenEvals/leaderboard-data |