# MiniMax-M2.7 vs Trinity Large Thinking

> MiniMax-M2.7 and Trinity Large Thinking score almost the same on the Noometry Index (37.7 vs 38.6), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. MiniMax-M2.7 scores higher in 6 categories and Trinity Large Thinking in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 25.9.
- The biggest single-benchmark swing is SciCode: 47% for MiniMax-M2.7 and 36.1% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- Trinity Large Thinking accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| Provider | MiniMax | Arcee AI |
| Noometry Index | 37.7 | 38.6 |
| Rank | 196 | 185 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $0.25 |
| Output $/M | $1.20 | $0.80 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.8 (#120)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1398 | 1238 |
| SciCode | 47% | 36.1% |
| LMArena Coding | 1454 | 1381 |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |

## Agentic & Tool Use

- MiniMax-M2.7: 25.1 (#111)
- Trinity Large Thinking: —

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.7 (#253)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 24.7% | 16.5% |
| CritPt | 0.6% | 0.9% |
| Thematic Generalization | 39.3% | 41.6% |
| LMArena Hard Prompts | 1422 | 1350 |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 145.85 | — |

## Math

- MiniMax-M2.7: 25.9 (#263)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1420 | 1366 |
| ProofBench | 3% | — |

## Knowledge

- MiniMax-M2.7: 37.7 (#152)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 6.9% |
| LMArena Expert | 1444 | 1360 |

## Multilingual

- MiniMax-M2.7: 50.3 (#123)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1382 | 1325 |
| LMArena Chinese | 1441 | 1373 |
| LMArena French | 1421 | 1374 |
| LMArena German | 1398 | 1356 |
| LMArena Japanese | 1262 | 1311 |
| LMArena Korean | 1313 | 1306 |
| LMArena Russian | 1383 | 1337 |
| LMArena Spanish | 1403 | 1357 |

## Instruction Following

- MiniMax-M2.7: 74.1 (#103)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1405 | 1334 |

## Long Context

- MiniMax-M2.7: 43.3 (#99)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1419 | 1355 |

## Writing & Preference

- MiniMax-M2.7: 58.9 (#112)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | MiniMax-M2.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1405 | 1340 |
| LMArena Creative Writing | 1354 | 1320 |
| LMArena Multi-Turn | 1412 | 1342 |

## FAQ

### Is MiniMax-M2.7 better than Trinity Large Thinking?

MiniMax-M2.7 and Trinity Large Thinking score almost the same on the Noometry Index (37.7 vs 38.6), so choose on price, context window or the category you care about most.

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

Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

### Is MiniMax-M2.7 or Trinity Large Thinking better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 205K.

### How many benchmarks do MiniMax-M2.7 and Trinity Large Thinking share?

23 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Trinity Large Thinking has 24.