# Claude Fable 5.1 vs GLM-4.7

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 41.7 on the Noometry Index. GLM-4.7 costs 20× 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-glm-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and GLM-4.7 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 23.7.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 6% for GLM-4.7.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 68.5 | 41.7 |
| Rank | 2 | 117 |
| Context | 1M | 205K |
| Input $/M | $10 | $0.60 |
| Output $/M | $50 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- GLM-4.7: 43.6 (#74)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena WebDev | 1753 | 1435 |
| SciCode | 63.1% | 45.1% |
| LMArena Coding | 1523 | 1454 |
| ALE-Bench | 2,143 | 399.48 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- GLM-4.7: 26.4 (#96)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| Vending-Bench 2 | 5,422 | 2,377 |
| Terminal-Bench | — | 33.4% |
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- GLM-4.7: 23.7 (#161)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| CritPt | 31.1% | 1.7% |
| Chess Puzzles | 47% | 6% |
| LMArena Hard Prompts | 1526 | 1443 |
| Epoch Capabilities Index | 165 | 143.53 |
| ARC-AGI-2 | 90% | — |
| SimpleBench | — | 47.7% |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |

## Math

- Claude Fable 5.1: 89.5 (#3)
- GLM-4.7: 37.7 (#92)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 83.3% |
| ProofBench | 100% | 6% |
| LMArena Math | 1519 | 1423 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- GLM-4.7: 47.0 (#74)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| SimpleQA Verified | 70.8% | 32.2% |
| LMArena Expert | 1528 | 1424 |
| GPQA Diamond | — | 83.3% |
| Humanity's Last Exam | 46.5% | — |
| Vectara Hallucination Rate | — | 11.7% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- GLM-4.7: —

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- GLM-4.7: 53.0 (#75)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1509 | 1417 |
| LMArena Chinese | 1589 | 1495 |
| LMArena French | 1532 | 1432 |
| LMArena German | 1495 | 1426 |
| LMArena Japanese | 1565 | 1439 |
| LMArena Russian | 1525 | 1423 |
| LMArena Spanish | 1503 | 1433 |
| LMArena Korean | — | 1401 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- GLM-4.7: 74.6 (#90)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1411 |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- GLM-4.7: 42.8 (#111)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1524 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- GLM-4.7: 61.1 (#89)

| Benchmark | Claude Fable 5.1 | GLM-4.7 |
|---|---|---|
| LMArena Text | 1511 | 1436 |
| LMArena Creative Writing | 1507 | 1401 |
| EQ-Bench Creative Writing | 2162 | 1413 |
| LMArena Multi-Turn | 1492 | 1446 |

## FAQ

### Is Claude Fable 5.1 better than GLM-4.7?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 41.7 on the Noometry Index. GLM-4.7 costs 20× 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 GLM-4.7?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or GLM-4.7 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 205K.

### How many benchmarks do Claude Fable 5.1 and GLM-4.7 share?

27 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and GLM-4.7 has 36.