# Claude 3.5 Sonnet vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.1 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-sonnet-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and Trinity Large Thinking in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 34.9 to 18.0.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| Provider | Anthropic | Arcee AI |
| Noometry Index | 34.4 | 38.1 |
| Rank | 225 | 180 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.5 Sonnet: 39.5 (#145)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1343 | 1381 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |

## Agentic & Tool Use

- Claude 3.5 Sonnet: 32.1 (#61)
- Trinity Large Thinking: —

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |

## Reasoning

- Claude 3.5 Sonnet: 22.5 (#176)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1350 |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| EnigmaEval | 0.9% | — |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |

## Math

- Claude 3.5 Sonnet: 18.0 (#282)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1306 | 1366 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Claude 3.5 Sonnet: 28.5 (#236)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1264 | 1359 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 6.9% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |

## Multimodal

- Claude 3.5 Sonnet: 26.0 (#115)
- Trinity Large Thinking: —

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |

## Multilingual

- Claude 3.5 Sonnet: 43.4 (#180)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1283 | 1325 |
| LMArena Chinese | 1271 | 1372 |
| LMArena French | 1304 | 1374 |
| LMArena German | 1297 | 1356 |
| LMArena Japanese | 1234 | 1312 |
| LMArena Korean | 1200 | 1304 |
| LMArena Russian | 1305 | 1338 |
| LMArena Spanish | 1289 | 1356 |

## Instruction Following

- Claude 3.5 Sonnet: 69.0 (#177)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1297 | 1334 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |

## Long Context

- Claude 3.5 Sonnet: 39.9 (#162)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1311 | 1355 |

## Writing & Preference

- Claude 3.5 Sonnet: 53.0 (#159)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | Claude 3.5 Sonnet | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1298 | 1340 |
| LMArena Creative Writing | 1292 | 1321 |
| LMArena Multi-Turn | 1326 | 1342 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |

## FAQ

### Is Claude 3.5 Sonnet better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.1 to 34.4 on the Noometry Index.

### Is Claude 3.5 Sonnet or Trinity Large Thinking better for coding?

Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 33.8 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Sonnet and Trinity Large Thinking share?

17 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Trinity Large Thinking has 24.