# Mercury 2 vs Trinity Large Thinking

> Mercury 2 and Trinity Large Thinking score almost the same on the Noometry Index (38.8 vs 38.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mercury-2-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 3 categories and Trinity Large Thinking in 4 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.0 to 16.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.3% for Mercury 2 and 6.9% for Trinity Large Thinking.
- Both cost about the same: $0.25 input and $0.75 output per million tokens.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| Provider | Inception | Arcee AI |
| Noometry Index | 38.8 | 38.1 |
| Rank | 167 | 180 |
| Context | 128K | 262K |
| Input $/M | $0.25 | $0.25 |
| Output $/M | $0.75 | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Mercury 2: 33.2 (#250)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1170 | 1238 |
| SciCode | 38.7% | 36.1% |
| LMArena Coding | 1391 | 1381 |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |

## Reasoning

- Mercury 2: 23.0 (#170)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| CritPt | 0.8% | 0.9% |
| LMArena Hard Prompts | 1362 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |

## Math

- Mercury 2: —
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | — | 1366 |

## Knowledge

- Mercury 2: 35.6 (#170)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 6.9% |
| LMArena Expert | 1358 | 1359 |

## Multilingual

- Mercury 2: 46.8 (#153)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1331 | 1325 |
| LMArena Chinese | 1416 | 1372 |
| LMArena Russian | 1303 | 1338 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1312 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1356 |

## Instruction Following

- Mercury 2: 70.4 (#161)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1328 | 1334 |

## Long Context

- Mercury 2: 40.4 (#149)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1329 | 1355 |

## Writing & Preference

- Mercury 2: 54.0 (#151)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | Mercury 2 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1355 | 1340 |
| LMArena Creative Writing | 1289 | 1321 |
| LMArena Multi-Turn | 1358 | 1342 |

## FAQ

### Is Mercury 2 better than Trinity Large Thinking?

Mercury 2 and Trinity Large Thinking score almost the same on the Noometry Index (38.8 vs 38.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Mercury 2 or Trinity Large Thinking?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

### Is Mercury 2 or Trinity Large Thinking better for coding?

They score almost the same on coding (33.2 vs 33.8); test both on your own repository before choosing.

### Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 128K.

### How many benchmarks do Mercury 2 and Trinity Large Thinking share?

15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Trinity Large Thinking has 24.