# Claude Fable 5.1 vs Trinity Large Thinking

> Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 52× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 90% for Claude Fable 5.1 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| Provider | Anthropic | Arcee AI |
| Noometry Index | 69.0 | 38.6 |
| Rank | 2 | 185 |
| Context | 1M | 262K |
| Input $/M | $10 | $0.25 |
| Output $/M | $50 | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 74.7 (#1)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1744 | 1238 |
| SciCode | 63.1% | 36.1% |
| LMArena Coding | 1528 | 1381 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.7 (#5)
- Trinity Large Thinking: —

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#7)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 90% | 16.5% |
| CritPt | 31.1% | 0.9% |
| LMArena Hard Prompts | 1526 | 1350 |
| ARC-AGI-2 | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 47% | — |
| Thematic Generalization | — | 41.6% |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 164.7 | — |

## Math

- Claude Fable 5.1: 89.6 (#4)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1525 | 1366 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.6 (#6)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1535 | 1360 |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| Vectara Hallucination Rate | — | 6.9% |

## Multimodal

- Claude Fable 5.1: 53.9 (#4)
- Trinity Large Thinking: —

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.1 (#3)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1507 | 1325 |
| LMArena Chinese | 1586 | 1373 |
| LMArena French | 1525 | 1374 |
| LMArena German | 1500 | 1356 |
| LMArena Japanese | 1543 | 1311 |
| LMArena Korean | 1534 | 1306 |
| LMArena Russian | 1521 | 1337 |
| LMArena Spanish | 1516 | 1357 |

## Instruction Following

- Claude Fable 5.1: 79.2 (#6)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1517 | 1334 |

## Long Context

- Claude Fable 5.1: 46.7 (#20)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1522 | 1355 |

## Writing & Preference

- Claude Fable 5.1: 79.2 (#2)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Claude Fable 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1510 | 1340 |
| LMArena Creative Writing | 1507 | 1320 |
| LMArena Multi-Turn | 1492 | 1342 |
| EQ-Bench Creative Writing | 2162 | — |

## FAQ

### Is Claude Fable 5.1 better than Trinity Large Thinking?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 52× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5.1 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; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or Trinity Large Thinking better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 262K.

### How many benchmarks do Claude Fable 5.1 and Trinity Large Thinking share?

21 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Trinity Large Thinking has 24.