# Claude Fable 5.1 vs Grok 4

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 47.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-grok-4
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and Grok 4 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 46.5.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 16% for Grok 4.

## Snapshot

| | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 68.5 | 47.8 |
| Rank | 2 | 49 |
| Context | 1M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- Grok 4: 49.9 (#44)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| WeirdML | 92.9% | 45.7% |
| LMArena Coding | 1523 | 1408 |
| FrontierCode | 50.9% | — |
| Aider Polyglot | — | 79.6% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- Grok 4: 32.1 (#62)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Remote Labor Index | 17.9% | — |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| GDP.pdf | 29.6% | — |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- Grok 4: 36.9 (#59)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 90% | 16% |
| ARC-AGI-1 | 97.5% | 66.7% |
| Chess Puzzles | 47% | 28% |
| LMArena Hard Prompts | 1526 | 1409 |
| Epoch Capabilities Index | 165 | 146.46 |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 90% | — |
| CritPt | 31.1% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| ForecastBench | — | 60.9 |

## Math

- Claude Fable 5.1: 89.5 (#3)
- Grok 4: 46.5 (#58)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 84% |
| LMArena Math | 1519 | 1422 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- Grok 4: 53.7 (#50)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Expert | 1528 | 1417 |
| GPQA Diamond | — | 87% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- Grok 4: 33.1 (#89)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Vision | 1319 | 1211 |
| GeoBench | — | 45% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- Grok 4: 52.0 (#98)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1509 | 1403 |
| LMArena Chinese | 1589 | 1428 |
| LMArena French | 1532 | 1418 |
| LMArena German | 1495 | 1429 |
| LMArena Japanese | 1565 | 1396 |
| LMArena Russian | 1525 | 1409 |
| LMArena Spanish | 1503 | 1419 |
| LMArena Korean | — | 1376 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- Grok 4: 79.4 (#4)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- Grok 4: 63.1 (#4)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1524 | 1409 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- Grok 4: 58.7 (#111)

| Benchmark | Claude Fable 5.1 | Grok 4 |
|---|---|---|
| LMArena Text | 1511 | 1412 |
| LMArena Creative Writing | 1507 | 1397 |
| LMArena Multi-Turn | 1492 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 2162 | — |
| WildBench | — | 79.7% |

## FAQ

### Is Claude Fable 5.1 better than Grok 4?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 47.8 on the Noometry Index.

### Is Claude Fable 5.1 or Grok 4 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 49.9 in the Noometry coding category.

### How many benchmarks do Claude Fable 5.1 and Grok 4 share?

23 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Grok 4 has 48.