# GLM-5.1 vs Inkling

> GLM-5.1 is the stronger model overall, scoring 47.8 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-inkling
- Last updated: 2026-10-11
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. GLM-5.1 scores higher in 6 categories and Inkling in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 31.3.
- The biggest single-benchmark swing is WeirdML: 57.1% for GLM-5.1 and 32.3% for Inkling.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- GLM-5.1 accepts more context: 200K tokens versus 66K.

## Snapshot

| | GLM-5.1 | Inkling |
|---|---|---|
| Provider | Z.ai (Zhipu) | Thinking Machines Lab |
| Noometry Index | 47.8 | 44.1 |
| Rank | 59 | 80 |
| Context | 200K | 66K |
| Input $/M | $1.40 | $1.87 |
| Output $/M | $4.40 | $4.68 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Inkling: 34.5 (#234)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| LMArena WebDev | 1508 | 1413 |
| SciCode | 43.8% | 47% |
| WeirdML | 57.1% | 32.3% |
| LMArena Coding | 1485 | 1464 |
| ALE-Bench | 887.1 | 946 |
| SWE-bench Verified | 74.2% | — |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Inkling: 29.6 (#85)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| APEX-Agents | 40.9% | 33.8% |
| τ²-bench Banking | — | 25% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Inkling: 40.4 (#56)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| SimpleBench | 55.1% | 50% |
| CritPt | 4.6% | 5.4% |
| Chess Puzzles | 19% | 21% |
| LMArena Hard Prompts | 1472 | 1451 |
| Epoch Capabilities Index | 149.84 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 79.5% |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |

## Math

- GLM-5.1: 49.7 (#60)
- Inkling: 31.3 (#225)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 33.3% |
| OTIS Mock AIME 2024-2025 | 93.3% | 88.9% |
| ProofBench | 22.2% | 0% |
| LMArena Math | 1473 | 1479 |
| FrontierMath Tier 4 | — | 4.9% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Inkling: 55.1 (#49)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| GPQA Diamond | 89.9% | 88.3% |
| SimpleQA Verified | 34% | 40.3% |
| LMArena Expert | 1476 | 1465 |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Inkling: 54.0 (#52)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| LMArena Non-English | 1447 | 1434 |
| LMArena Chinese | 1515 | 1490 |
| LMArena French | 1474 | 1458 |
| LMArena German | 1465 | 1446 |
| LMArena Japanese | 1434 | 1429 |
| LMArena Korean | 1418 | 1404 |
| LMArena Russian | 1454 | 1429 |
| LMArena Spanish | 1469 | 1448 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Inkling: 75.1 (#71)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1451 | 1426 |

## Long Context

- GLM-5.1: 44.9 (#53)
- Inkling: 43.8 (#86)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| LMArena Longer Query | 1466 | 1434 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Inkling: 65.2 (#51)

| Benchmark | GLM-5.1 | Inkling |
|---|---|---|
| LMArena Text | 1461 | 1441 |
| LMArena Creative Writing | 1453 | 1387 |
| EQ-Bench Creative Writing | 1592 | 1611 |
| LMArena Multi-Turn | 1472 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is GLM-5.1 better than Inkling?

GLM-5.1 is the stronger model overall, scoring 47.8 to 44.1 on the Noometry Index.

### Which is cheaper, GLM-5.1 or Inkling?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is GLM-5.1 or Inkling better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 66K.

### How many benchmarks do GLM-5.1 and Inkling share?

32 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Inkling has 41.