# MiniMax M2.7 vs Trinity-Large-Thinking

> Side-by-side benchmark comparison for MiniMax M2.7 and Trinity-Large-Thinking across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minimax-m2-7-vs-trinity-large-thinking
- Last updated: September 29, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick MiniMax M2.7 if you want the stronger benchmark profile. Trinity-Large-Thinking only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- MiniMax M2.7 leads overall 48.04 to 34.23.
- The clearest category separation is in reasoning, where the averages are 76.1 for MiniMax M2.7 and 48.3 for Trinity-Large-Thinking.
- The biggest single benchmark swing is AIME25 (Arcee) in Mathematics, with scores of 80.0% and 96.3%.
- Trinity-Large-Thinking is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Trinity-Large-Thinking also has the larger context window at 512K.

## Model Snapshot

| Property | MiniMax M2.7 | Trinity-Large-Thinking |
|----------|----------|----------|
| Creator | MiniMax | Arcee AI |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 512K |
| Overall Score | 48.04 | 34.23 |
| Benchmarks Covered | 23 | 5 |
| Pricing (input/output) | $0.30 / $1.20 | $0.25 / $0.90 |

## Category Breakdown

### Agentic

- Winner: Directional only
- MiniMax M2.7 public-lane score: 29 (Supported · #82/117)
- Trinity-Large-Thinking public-lane score: 17.7 (Estimated · #104/117)

| Benchmark | MiniMax M2.7 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 57% | Coming soon | Coming soon |
| Toolathlon | 46.3% | Coming soon | Coming soon |
| MLE-Bench Lite | 66.6% | Coming soon | Coming soon |
| MM-ClawBench | 62.7% | Coming soon | Coming soon |
| Claw-Eval | 48.7% | Coming soon | Coming soon |
| Gert Labs | 40.40% | 32.55% | MiniMax M2.7 |
| Terminal-Bench 2.1 (Vals) | 48.7% | Coming soon | Coming soon |

### Coding

- Winner: MiniMax M2.7
- MiniMax M2.7 public-lane score: 36 (Supported · #76/142)
- Trinity-Large-Thinking public-lane score: 21 (Supported · #119/142)

| Benchmark | MiniMax M2.7 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified* | 75.4% | 63.2% | MiniMax M2.7 |
| SWE-bench Pro | 56.2% | Coming soon | Coming soon |
| SWE-Rebench | 51.9% | Coming soon | Coming soon |
| SWE Multilingual | 76.5% | Coming soon | Coming soon |
| Multi-SWE Bench | 52.7% | Coming soon | Coming soon |
| VIBE-Pro | 55.6% | Coming soon | Coming soon |
| NL2Repo | 39.8% | Coming soon | Coming soon |
| Vibe Code Bench | 27.04% | Coming soon | Coming soon |
| React Native Evals | 71.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 79.9% | Coming soon | Coming soon |
| SWE-bench (Vals) | 73.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 76.1 (Unranked · 2 rankable rows)
- Trinity-Large-Thinking public-lane score: 48.3 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Directional only
- MiniMax M2.7 public-lane score: 43.1 (Supported · #86/168)
- Trinity-Large-Thinking public-lane score: 35.9 (Estimated · #114/168)

| Benchmark | MiniMax M2.7 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 87.0% | 76.3% | MiniMax M2.7 |
| MMLU-Pro (Arcee) | 80.8% | 83.4% | Trinity-Large-Thinking |
| GPQA Diamond (Vals) | 86.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 80.4% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- MiniMax M2.7 public-lane score: 91.6 (#10/124)
- Trinity-Large-Thinking public-lane score: 66.3 (#68/124)

### Mathematics

- Winner: Not comparable
- MiniMax M2.7 public-lane score: Coming soon
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | MiniMax M2.7 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | 80.0% | 96.3% | Trinity-Large-Thinking |

## FAQ

### Which is better overall, MiniMax M2.7 or Trinity-Large-Thinking?

MiniMax M2.7 is ahead overall on BenchLM right now.

### Where is the biggest gap between MiniMax M2.7 and Trinity-Large-Thinking?

The widest category gap is in reasoning, where the averages are 76.1 for MiniMax M2.7 and 48.3 for Trinity-Large-Thinking.

### How many benchmarks does MiniMax M2.7 cover on BenchLM?

MiniMax M2.7 currently has 23 sourced benchmark scores on BenchLM.

### How many benchmarks does Trinity-Large-Thinking cover on BenchLM?

Trinity-Large-Thinking currently has 5 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniMax M2.7 vs Trinity-Large-Preview](/compare/minimax-m2-7-vs-trinity-large-preview)
- [Trinity-Large-Thinking vs Trinity-Large-Preview](/compare/trinity-large-preview-vs-trinity-large-thinking)
- [MiniMax M2.7 vs GPT-6 Astra](/compare/gpt-6-astra-vs-minimax-m2-7)
- [Trinity-Large-Thinking vs GPT-6 Astra](/compare/gpt-6-astra-vs-trinity-large-thinking)

## Explore More

- [MiniMax M2.7 profile](/models/minimax-m2-7)
- [Trinity-Large-Thinking profile](/models/trinity-large-thinking)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)