# Claude Fable 5 vs DeepSeek-V2 (MoE-236B, May 2024)

> Claude Fable 5 has enough public results to be ranked (#5); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/claude-fable-5-vs-deepseek-v2
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Claude Fable 5 scores higher in 1 category and DeepSeek-V2 (MoE-236B, May 2024) in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5 leads 67.0 to 39.8.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 66.3 | 39.7 |
| Rank | 5 | — |
| Context | 1M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5: 67.0 (#4)
- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| LMArena WebDev | 1626 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| WeirdML | 91.9% | — |
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | 1519 | — |
| MirrorCode | 63.9% | — |
| BigCodeBench Complete | — | 59.4% |
| ALE-Bench | 2,041 | — |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 163.6 | 124.78 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| NYT Connections (extended) | 92.7% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 28.6% | — |
| Chess Puzzles | 41% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| LMArena Hard Prompts | 1508 | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
| BIG-Bench Hard | — | 78.8% |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |

## Math

- Claude Fable 5: 88.4 (#5)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 95% | — |
| LMArena Math | 1519 | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| GPQA Diamond | 85.9% | — |
| SimpleQA Verified | 70.7% | — |
| LMArena Expert | 1534 | — |
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Vision | 1326 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1483 | — |
| LMArena Chinese | 1546 | — |
| LMArena French | 1509 | — |
| LMArena German | 1486 | — |
| LMArena Japanese | 1507 | — |
| LMArena Korean | 1493 | — |
| LMArena Russian | 1507 | — |
| LMArena Spanish | 1503 | — |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1503 | — |

## Long Context

- Claude Fable 5: 46.3 (#22)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1510 | — |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- DeepSeek-V2 (MoE-236B, May 2024): —

| Benchmark | Claude Fable 5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1491 | — |
| LMArena Creative Writing | 1494 | — |
| EQ-Bench Creative Writing | 1943 | — |
| EQ-Bench 4 | 1340 | — |
| LMArena Multi-Turn | 1505 | — |

## FAQ

### Is Claude Fable 5 better than DeepSeek-V2 (MoE-236B, May 2024)?

Claude Fable 5 has enough public results to be ranked (#5); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is Claude Fable 5 or DeepSeek-V2 (MoE-236B, May 2024) better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 39.8 in the Noometry coding category.

### How many benchmarks do Claude Fable 5 and DeepSeek-V2 (MoE-236B, May 2024) share?

1 benchmark has published results for both models. Claude Fable 5 has 61 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.