# Claude 3 Haiku vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 9.8.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| Provider | Anthropic | Arcee AI |
| Noometry Index | 25.9 | 38.6 |
| Rank | 340 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1199 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1350 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1188 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1148 | 1360 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 6.9% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Trinity Large Thinking: —

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1178 | 1325 |
| LMArena Chinese | 1155 | 1373 |
| LMArena French | 1195 | 1374 |
| LMArena German | 1174 | 1356 |
| LMArena Japanese | 1102 | 1311 |
| LMArena Korean | 1109 | 1306 |
| LMArena Russian | 1204 | 1337 |
| LMArena Spanish | 1166 | 1357 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1173 | 1334 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1190 | 1355 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Claude 3 Haiku | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1195 | 1340 |
| LMArena Creative Writing | 1157 | 1320 |
| LMArena Multi-Turn | 1190 | 1342 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Trinity Large Thinking share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Trinity Large Thinking has 24.