# Claude Fable 5 vs GLM-5.1

> Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.6 on the Noometry Index. GLM-5.1 costs 9.3× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-vs-glm-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and GLM-5.1 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 49.0.
- The biggest single-benchmark swing is GBAEval: 74.5% for Claude Fable 5 and 0% for GLM-5.1.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 66.3 | 47.6 |
| Rank | 5 | 51 |
| Context | 1M | 200K |
| Input $/M | $10 | $1.40 |
| Output $/M | $50 | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5: 67.0 (#4)
- GLM-5.1: 48.5 (#52)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena WebDev | 1626 | 1509 |
| SciCode | 61% | 43.8% |
| WeirdML | 91.9% | 57.1% |
| LMArena Coding | 1519 | 1486 |
| ALE-Bench | 2,041 | 887.1 |
| SWE-bench Verified | — | 74.2% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| FrontierSWE | 47% | — |
| MirrorCode | 63.9% | — |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- GLM-5.1: 24.8 (#106)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| APEX-Agents | 63.6% | 40.9% |
| GBAEval | 74.5% | 0% |
| Vending-Bench 2 | 5,680 | 5,634 |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| ExploitBench | — | 18.1% |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- GLM-5.1: 38.2 (#57)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| SimpleBench | 81.9% | 55.1% |
| NYT Connections (extended) | 92.7% | 77.7% |
| CritPt | 28.6% | 4.6% |
| Chess Puzzles | 41% | 19% |
| LMArena Hard Prompts | 1508 | 1472 |
| Epoch Capabilities Index | 163.6 | 149.86 |
| ARC-AGI-2 | 89.2% | — |
| Kagi LLM Benchmark | 91.4% | — |
| ARC-AGI-1 | 98.5% | — |
| EnigmaEval | 39.3% | — |
| Thematic Generalization | — | 69.8% |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |

## Math

- Claude Fable 5: 88.4 (#5)
- GLM-5.1: 49.0 (#48)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 36.8% |
| OTIS Mock AIME 2024-2025 | 100% | 93.3% |
| ProofBench | 95% | 22.2% |
| LMArena Math | 1519 | 1472 |
| FrontierMath Tier 4 | 90.2% | — |
| MathArena Final-Answer Competitions | — | 67.1% |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- GLM-5.1: 55.0 (#45)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 85.9% | 89.9% |
| SimpleQA Verified | 70.7% | 34% |
| LMArena Expert | 1534 | 1477 |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- GLM-5.1: —

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena Vision | 1326 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- GLM-5.1: 55.2 (#34)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1483 | 1448 |
| LMArena Chinese | 1546 | 1516 |
| LMArena French | 1509 | 1478 |
| LMArena German | 1486 | 1466 |
| LMArena Japanese | 1507 | 1436 |
| LMArena Korean | 1493 | 1423 |
| LMArena Russian | 1507 | 1453 |
| LMArena Spanish | 1503 | 1467 |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- GLM-5.1: 76.5 (#41)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1503 | 1451 |

## Long Context

- Claude Fable 5: 46.3 (#22)
- GLM-5.1: 44.9 (#51)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1510 | 1467 |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- GLM-5.1: 67.2 (#29)

| Benchmark | Claude Fable 5 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1491 | 1462 |
| LMArena Creative Writing | 1494 | 1454 |
| EQ-Bench Creative Writing | 1943 | 1592 |
| LMArena Multi-Turn | 1505 | 1473 |
| EQ-Bench 4 | 1340 | — |

## FAQ

### Is Claude Fable 5 better than GLM-5.1?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 47.6 on the Noometry Index. GLM-5.1 costs 9.3× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5 or GLM-5.1?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Claude Fable 5 or GLM-5.1 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 48.5 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 200K.

### How many benchmarks do Claude Fable 5 and GLM-5.1 share?

35 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and GLM-5.1 has 41.