Data points: 84
Model compare
The readout for MiniMax M2.1 and MiniMax M2.5, before the detailed comparison sheet.
Weighted outcome: MiniMax M2.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
MiniMax M2.1
MiniMax M2.1 has the higher weighted result; Model A / B score 88 to 12.
Evidence depth
84 data points
Includes 9 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with MiniMax M2.1
The charts below split 17 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for MiniMax M2.1 and MiniMax M2.5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | MiniMax M2.1 | MiniMax M2.5 |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 88.0 pts | 12.0 pts |
| Benchmark category leads | 2 categories | 0 categories |
| Operational advantages | Average speed, First-token latency | Cheapest input price, Free providers, Provider coverage |
| Context window | 204.8K tokens | 204.8K tokens |
| Max output | 131.1K tokens | 196.6K tokens |
| Modalities | Input Text Output Text | Input Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | MiniMax M2.1 | MiniMax M2.5 |
|---|---|---|
| Developer | MiniMax | MiniMax |
| Released | Dec 2025 | Feb 2026 |
| Parameters | No data | No data |
| Tokenizer | Other | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | minimax/minimax-m2.1 | minimax/minimax-m2.5 |
| References | No data | No data |
This report only uses LMSpeed data for MiniMax M2.1 and MiniMax M2.5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
MiniMax M2.1
MiniMax M2.1 is stronger in benchmark categories (Coding, Reasoning) and operational dimensions (Average speed, First-token latency).
MiniMax M2.5
MiniMax M2.5 has these operational advantages: Cheapest input price, Free providers, Provider coverage.
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
MiniMax M2.1
54.9
Avg. score
MiniMax M2.5
53
No data
MiniMax M2.1 leads by 5.4
MiniMax M2.1 leads by 1.8
No data
MiniMax M2.1
No data
No data
No data
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
MiniMax M2.1
winner1.01 s
Rank #59/139 · confidence 4
MiniMax M2.5
1.15 s
Rank #71/139 · confidence 4
MiniMax M2.1
75.3 tok/s
Rank #82/139 · confidence 4
MiniMax M2.5
winner78.0 tok/s
Rank #78/139 · confidence 4
MiniMax M2.1
27.56 s
Rank #102/139 · confidence 4
MiniMax M2.5
winner26.80 s
Rank #100/139 · confidence 4
MiniMax M2.1
$0.525/M
Rank #42/163 · confidence 4
MiniMax M2.5
$0.525/M
Rank #42/163 · confidence 4
MiniMax M2.1
$1.20/M
Rank #44/163 · confidence 4
MiniMax M2.5
$1.20/M
Rank #44/163 · confidence 4
MiniMax M2.1
$0.300/M
Rank #46/163 · confidence 4
MiniMax M2.5
$0.300/M
Rank #46/163 · confidence 4
MiniMax M2.1
83.0%
Rank #57/187 · confidence 4
MiniMax M2.5
winner84.8%
Rank #45/187 · confidence 4
MiniMax M2.1
winner22.2%
Rank #49/186 · confidence 4
MiniMax M2.5
19.1%
Rank #59/186 · confidence 4
MiniMax M2.1
40.7%
Rank #60/184 · confidence 4
MiniMax M2.5
winner42.6%
Rank #45/184 · confidence 4
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | MiniMax M2.1 | MiniMax M2.5 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | MiniMax M2.1 | MiniMax M2.5 |
|---|---|---|
75 tests | MiniMax M2.1 speed / latency 86 tok/s / 2879ms input / output No data | MiniMax M2.5 speed / latency 79 tok/s / 3192ms input / output No data |
30 tests | MiniMax M2.1 speed / latency N/A / N/A input / output No data | MiniMax M2.5 speed / latency 53 tok/s / 5949ms input / output No data |
29 tests | MiniMax M2.1 speed / latency N/A / N/A input / output No data | MiniMax M2.5 speed / latency 55 tok/s / 12842ms input / output No data |
20 tests | MiniMax M2.1 speed / latency N/A / N/A input / output No data | MiniMax M2.5 speed / latency 71 tok/s / 8578ms input / output No data |
10 tests | MiniMax M2.1 minimax-m2.1-free speed / latency 60 tok/s / 4511ms input / output $0.010/request | MiniMax M2.5 minimax-m2.5 speed / latency 19 tok/s / 19888ms input / output $0.010/request |
MiniMax M2.1 minimax-m2.1 speed / latency No data input / output $0/M/$0/M | MiniMax M2.5 minimax-m2.5 speed / latency No data input / output $0/M | |
MiniMax M2.1 minimax-m2.1 speed / latency No data input / output $0.021/M/$0.082/M | MiniMax M2.5 minimax-m2.5 speed / latency No data input / output $0.021/M | |
MiniMax M2.1 minimax-m2.1 speed / latency No data input / output $0.010/request | MiniMax M2.5 minimax-m2.5 speed / latency No data input / output $0.010/request |
Weighted outcome: MiniMax M2.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputText outputTool callingJSON modeReasoning | Text inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
