Quality
#56/750
Overall quality score
🇨🇳MiniMaxOpen sourceMiniMax: MiniMax M2.5.
See how MiniMax: MiniMax M2.5 compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#23/7595 t/s
Output tokens per second
Input price
#28/75$0.15/1M
Per 1M tokens
Output price
#31/75$0.90/1M
Per 1M tokens
Context
#60/75204.8K
Content read at once
Comparison summary
MiniMax: MiniMax M2.5 ranks #56 of 75 for overall quality and #23 for response speed in the current catalogue.
Its listed input price is $0.15/1M, output price is $0.90/1M, and it can work with up to 204.8K of context at once.
Its strongest areas in the current data are everyday help, coding, complex tasks.
Practical specifications
- Company
- MiniMax
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text
- Output
- Text
- Context window
- 204.8K
MiniMax: MiniMax M2.5 technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | MiniMax M2.5 | Source |
|---|---|---|---|
| GPQA | GPQA Diamond | 84.8 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 19.1 | OpenRouter model benchmarks |
| IFBench | IFBench | 71.6 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 95.3 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 66 | OpenRouter model benchmarks |
| CritPt | CritPt | 1.1 | OpenRouter model benchmarks |
| SciCode | SciCode | 42.6 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 34.8 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 26.2 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 10.7 | OpenRouter model benchmarks |
| SWE-bench Pro | Coding | 55.4 | OpenEvals/leaderboard-data |
| SWE-bench Verified | Coding | 75.8 | OpenEvals/leaderboard-data |
Quality benchmarks
See where MiniMax: MiniMax M2.5 stands.
The darker bar marks MiniMax: MiniMax M2.5; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better