# Ministral 3B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 26.2 on the Noometry Index. Ministral 3B costs 3.9× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/ministral-3b-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Ministral 3B scores higher in 1 category and Trinity Large Thinking in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 10.4.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 131K.

## Snapshot

| | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 26.2 | 38.6 |
| Rank | 338 | 185 |
| Context | 131K | 262K |
| Input $/M | $0.10 | $0.25 |
| Output $/M | $0.10 | $0.80 |
| Weights | Open | Open |

## Coding

- Ministral 3B: —
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| LMArena Coding | — | 1381 |

## Reasoning

- Ministral 3B: 18.4 (#282)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 118.1 | — |

## Math

- Ministral 3B: 26.6 (#258)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | — | 1366 |
| MATH Level 5 | 14.4% | — |

## Knowledge

- Ministral 3B: 10.4 (#302)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 7.3% | 6.9% |
| GPQA Diamond | 25.3% | — |
| LMArena Expert | — | 1360 |

## Multilingual

- Ministral 3B: —
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |

## Instruction Following

- Ministral 3B: —
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |

## Long Context

- Ministral 3B: —
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |

## Writing & Preference

- Ministral 3B: —
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Ministral 3B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |

## FAQ

### Is Ministral 3B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 26.2 on the Noometry Index. Ministral 3B costs 3.9× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

### Which is cheaper, Ministral 3B or Trinity Large Thinking?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

### Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 131K.

### How many benchmarks do Ministral 3B and Trinity Large Thinking share?

1 benchmark has published results for both models. Ministral 3B has 6 scored results on Noometry and Trinity Large Thinking has 24.