Data points: 80
The readout for MiniMax M2.5 and Trinity Large Thinking, before the detailed comparison sheet.
Decision read
MiniMax M2.5
MiniMax M2.5 currently has the stronger profile, with verified wins split 4 to 2.
Evidence depth
80 data points
Includes 9 benchmark rows, 0 audit samples, and 5 provider examples.
Selection signal
Start with MiniMax M2.5
The charts below split 14 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.
Model compare MiniMax M2.5 vs Trinity Large Thinkingminimax-m2-5-vs-trinity-large-thinking | Model A MiniMax M2.5 | Model B Trinity Large Thinking |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 2 wins |
| Where it leads | Cheapest input price, Free providers, Provider coverage, Recent tests |
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 M2.5
40.4
Avg. score
Trinity Large Thinking
62.7
Selected category
Reasoning
MiniMax M2.5 leads by 21.0
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
MiniMax M2.5
75.9 tok/s
Rank #83/139 · confidence 4
Trinity Large Thinking
winner212.2 tok/s
Rank #14/139 · confidence 4
MiniMax M2.5
1.40 s
Rank #80/139 · confidence 4
Trinity Large Thinking
winner0.71 s
Rank #30/139 · confidence 4
MiniMax M2.5
27.76 s
Rank #105/139 · confidence 4
Trinity Large Thinking
winner10.13 s
Rank #73/139 · confidence 4
MiniMax M2.5
$0.525/M
Rank #43/167 · confidence 4
Trinity Large Thinking
winner$0.395/M
Rank #35/167 · confidence 4
MiniMax M2.5
$0.300/M
Rank #47/167 · confidence 4
Trinity Large Thinking
winner$0.235/M
Rank #36/167 · confidence 4
MiniMax M2.5
$1.20/M
Rank #45/167 · confidence 4
Trinity Large Thinking
winner$0.875/M
Rank #38/167 · confidence 4
MiniMax M2.5
winner84.8%
Rank #44/187 · confidence 4
Trinity Large Thinking
75.2%
Rank #92/187 · confidence 4
MiniMax M2.5
winner19.1%
Rank #58/186 · confidence 4
Trinity Large Thinking
14.7%
Rank #73/186 · confidence 4
MiniMax M2.5
winner42.6%
Rank #44/184 · confidence 4
Trinity Large Thinking
36.1%
Rank #102/184 · confidence 4
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | MiniMax M2.5 | Trinity Large Thinking |
|---|---|---|
| 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 M2.5 | Trinity Large Thinking |
|---|---|---|
10 tests | MiniMax M2.5 speed / latency 49 tok/s / 9384ms input / output No data | Trinity Large Thinking |
This report only uses LMSpeed data for MiniMax M2.5 and Trinity Large Thinking: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | MiniMax M2.5 | Trinity Large Thinking |
|---|---|---|
| When to choose each model | MiniMax M2.5 MiniMax M2.5 is stronger when you prioritize Cheapest input price, Free providers, Provider coverage, Recent tests. | Trinity Large Thinking Trinity Large Thinking is stronger when you prioritize Average speed, First-token latency. |
TL;DR: MiniMax M2.5 leads across 80 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from MiniMax M2.5 vs Trinity Large Thinking into nearby model comparisons with enough verified LMSpeed data.
| Average speed, First-token latency |
| Model metadata | MiniMax M2.5 exposes 204.8K tokens; notable signals: Text input, Text output, Tool calling, Structured outputs. | Trinity Large Thinking exposes 262.1K tokens; notable signals: Text input, Text output, Tool calling, Reasoning. |
|---|---|---|
| Developer | MiniMax | Arcee AI |
| Context window | 204.8K tokens | 262.1K tokens |
| Max output | 196.6K tokens | 80K tokens |
| Released | Feb 2026 | Apr 2026 |
| Modalities | Input Text Output Text | Input Text Output Text |
| Features | Text inputText outputTool callingStructured outputsJSON modeReasoning | Text inputText outputTool callingReasoning |
| Parameters | No data | No data |
| Tokenizer | Other | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | minimax/minimax-m2.5 | arcee-ai/trinity-large-thinking |
| References | No data | No data |
speed / latency
108 tok/s / 1942ms
input / output
No data
AI API0 tests | MiniMax M2.5 speed / latency N/A / N/A input / output No data | Trinity Large Thinking speed / latency N/A / N/A input / output No data |
|---|
Dext API0 tests | MiniMax M2.5 minimax/minimax-m2.5 speed / latency N/A / N/A input / output $0.025/M/$0.099/M | Trinity Large Thinking arcee-ai/trinity-large-thinking speed / latency N/A / N/A input / output $0.010/M/$0.037/M |
|---|
Koru API0 tests | MiniMax M2.5 speed / latency N/A / N/A input / output No data | Trinity Large Thinking speed / latency N/A / N/A input / output No data |
|---|
OpenRouter0 tests | MiniMax M2.5 speed / latency N/A / N/A input / output No data | Trinity Large Thinking speed / latency N/A / N/A input / output No data |
|---|
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
