# Claude Fable 5.1 vs DeepSeek-R1

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 42.0 on the Noometry Index. DeepSeek-R1 costs 22× 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-deepseek-r1
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and DeepSeek-R1 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 18.7.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 1.3% for DeepSeek-R1.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 164K.

## Snapshot

| | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 68.5 | 42.0 |
| Rank | 2 | 110 |
| Context | 1M | 164K |
| Input $/M | $10 | $0.50 |
| Output $/M | $50 | $2.15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- DeepSeek-R1: 45.9 (#63)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| SciCode | 63.1% | 35.7% |
| WeirdML | 92.9% | 41.6% |
| LMArena Coding | 1523 | 1427 |
| ALE-Bench | 2,143 | 804.12 |
| FrontierCode | 50.9% | — |
| Aider Polyglot | — | 71.4% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1753 | — |
| FrontierSWE | 56.3% | — |
| LiveBench Coding | — | 66.7% |
| MirrorCode | 73.3% | — |
| AlgoTune | — | 1.7 |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- DeepSeek-R1: 30.4 (#68)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| GDP.pdf | 29.6% | — |
| METR Time Horizons | — | 53.8% |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- DeepSeek-R1: 18.7 (#253)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| ARC-AGI-2 | 90% | 1.3% |
| ARC-AGI-1 | 97.5% | 21.2% |
| CritPt | 31.1% | 1.1% |
| LMArena Hard Prompts | 1526 | 1415 |
| Epoch Capabilities Index | 165 | 141.3 |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 90% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| LiveBench Reasoning | — | 83.2% |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LiveBench Data Analysis | — | 69.8% |
| LMCA | 65.5% | — |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |

## Math

- Claude Fable 5.1: 89.5 (#3)
- DeepSeek-R1: 42.0 (#70)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 66.4% |
| LMArena Math | 1519 | 1401 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- DeepSeek-R1: 44.3 (#81)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Expert | 1528 | 1394 |
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- DeepSeek-R1: —

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- DeepSeek-R1: 52.6 (#80)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1509 | 1412 |
| LMArena Chinese | 1589 | 1443 |
| LMArena French | 1532 | 1415 |
| LMArena German | 1495 | 1405 |
| LMArena Japanese | 1565 | 1394 |
| LMArena Russian | 1525 | 1423 |
| LMArena Spanish | 1503 | 1410 |
| LMArena Korean | — | 1359 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- DeepSeek-R1: 72.2 (#138)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- DeepSeek-R1: 45.4 (#36)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1524 | 1391 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- DeepSeek-R1: 61.5 (#84)

| Benchmark | Claude Fable 5.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1511 | 1428 |
| LMArena Creative Writing | 1507 | 1406 |
| EQ-Bench Creative Writing | 2162 | 1500 |
| LMArena Multi-Turn | 1492 | 1404 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |

## FAQ

### Is Claude Fable 5.1 better than DeepSeek-R1?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 42.0 on the Noometry Index. DeepSeek-R1 costs 22× 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 DeepSeek-R1?

DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or DeepSeek-R1 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 45.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 164K.

### How many benchmarks do Claude Fable 5.1 and DeepSeek-R1 share?

25 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and DeepSeek-R1 has 52.