# Magistral Small vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-small-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Magistral Small scores higher in 1 category and Trinity Large Thinking in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 26.2.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.

## Snapshot

| | Magistral Small | Trinity Large Thinking |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 30.2 | 38.6 |
| Rank | 296 | 185 |
| Context | 128K | 262K |
| Input $/M | $0.50 | $0.25 |
| Output $/M | $1.50 | $0.80 |
| Weights | Open | Open |

## Coding

- Magistral Small: 38.4 (#176)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| SciCode | 35.2% | 36.1% |
| LMArena WebDev | — | 1238 |
| LMArena Coding | — | 1381 |

## Reasoning

- Magistral Small: 6.8 (#350)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| CritPt | 0.3% | 0.9% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 5% | — |
| Chess Puzzles | 3% | — |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| DTBench | 61.3% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 133.19 | — |

## Math

- Magistral Small: 26.2 (#261)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| LMArena Math | — | 1366 |

## Knowledge

- Magistral Small: 30.9 (#223)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |

## Multilingual

- Magistral Small: —
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Magistral Small | 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

- Magistral Small: —
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |

## Long Context

- Magistral Small: —
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |

## Writing & Preference

- Magistral Small: —
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Magistral Small | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |

## FAQ

### Is Magistral Small better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.2 on the Noometry Index.

### Which is cheaper, Magistral Small 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; Magistral Small lists at $0.50 and $1.50.

### Is Magistral Small or Trinity Large Thinking better for coding?

Magistral Small scores higher on coding benchmarks: 38.4 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Magistral Small and Trinity Large Thinking share?

2 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Trinity Large Thinking has 24.