# Granite 3.0 2b Instruct vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 29.6.

## Snapshot

| | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| Provider | IBM | Arcee AI |
| Noometry Index | 30.8 | 38.6 |
| Rank | 286 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 28.3 (#316)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1090 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 20.5% | — |

## Reasoning

- Granite 3.0 2b Instruct: 20.5 (#235)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |

## Math

- Granite 3.0 2b Instruct: 32.2 (#217)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1117 | 1366 |

## Knowledge

- Granite 3.0 2b Instruct: 29.0 (#241)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1064 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |

## Multilingual

- Granite 3.0 2b Instruct: 27.0 (#278)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1033 | 1325 |
| LMArena Chinese | 1070 | 1373 |
| LMArena Russian | 1045 | 1337 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Spanish | — | 1357 |

## Instruction Following

- Granite 3.0 2b Instruct: 53.9 (#284)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1056 | 1334 |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#268)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1070 | 1355 |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.6 (#292)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Granite 3.0 2b Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1080 | 1340 |
| LMArena Creative Writing | 1046 | 1320 |
| LMArena Multi-Turn | 1053 | 1342 |

## FAQ

### Is Granite 3.0 2b Instruct better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.8 on the Noometry Index.

### Is Granite 3.0 2b Instruct or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 28.3 in the Noometry coding category.

### How many benchmarks do Granite 3.0 2b Instruct and Trinity Large Thinking share?

12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Trinity Large Thinking has 24.