# GLM-5.1 vs Trinity Large Thinking

> GLM-5.1 is the stronger model overall, scoring 47.6 to 38.1 on the Noometry Index. Trinity Large Thinking costs 5.5× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GLM-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 GLM-5.1 leads 38.2 to 16.3.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-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 $1.40 / $4.40 for GLM-5.1.
- Trinity Large Thinking accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| Provider | Z.ai (Zhipu) | Arcee AI |
| Noometry Index | 47.6 | 38.1 |
| Rank | 51 | 180 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $0.25 |
| Output $/M | $4.40 | $0.80 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1509 | 1238 |
| SciCode | 43.8% | 36.1% |
| LMArena Coding | 1486 | 1381 |
| SWE-bench Verified | 74.2% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Trinity Large Thinking: —

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 77.7% | 16.5% |
| CritPt | 4.6% | 0.9% |
| Thematic Generalization | 69.8% | 41.6% |
| LMArena Hard Prompts | 1472 | 1350 |
| SimpleBench | 55.1% | — |
| Chess Puzzles | 19% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 149.86 | — |

## Math

- GLM-5.1: 49.0 (#48)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1472 | 1366 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1477 | 1359 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 6.9% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1448 | 1325 |
| LMArena Chinese | 1516 | 1372 |
| LMArena French | 1478 | 1374 |
| LMArena German | 1466 | 1356 |
| LMArena Japanese | 1436 | 1312 |
| LMArena Korean | 1423 | 1304 |
| LMArena Russian | 1453 | 1338 |
| LMArena Spanish | 1467 | 1356 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1451 | 1334 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1467 | 1355 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | GLM-5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1462 | 1340 |
| LMArena Creative Writing | 1454 | 1321 |
| LMArena Multi-Turn | 1473 | 1342 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Trinity Large Thinking?

GLM-5.1 is the stronger model overall, scoring 47.6 to 38.1 on the Noometry Index. Trinity Large Thinking costs 5.5× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-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; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Trinity Large Thinking better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Trinity Large Thinking share?

22 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Trinity Large Thinking has 24.