# Claude 2 vs DeepSeek-V3

> DeepSeek-V3 is the stronger model overall, scoring 39.2 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-deepseek-v3
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Claude 2 scores higher in 1 category and DeepSeek-V3 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3 leads 30.4 to 8.7.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 75.5% for DeepSeek-V3.
- DeepSeek-V3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | DeepSeek-V3 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 24.7 | 39.2 |
| Rank | 342 | 157 |
| Context | — | 164K |
| Input $/M | — | $0.24 |
| Output $/M | — | $0.90 |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- DeepSeek-V3: 41.9 (#99)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| HumanEval+ | 61.6% | 86.6% |
| Aider Polyglot | — | 55.1% |
| SciCode | — | 35.8% |
| WeirdML | — | 36.1% |
| BigCodeBench Instruct | — | 50% |
| LiveBench Coding | — | 70.9% |
| LMArena Coding | — | 1368 |
| BigCodeBench Complete | — | 62.2% |
| MBPP+ | — | 73% |

## Agentic & Tool Use

- Claude 2: —
- DeepSeek-V3: —

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| METR Time Horizons | — | 49.6% |

## Reasoning

- Claude 2: 20.8 (#213)
- DeepSeek-V3: 20.0 (#226)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| DTBench | 51.9% | 64.8% |
| Epoch Capabilities Index | 120.08 | 135.95 |
| SimpleBench | — | 27.2% |
| Kagi LLM Benchmark | — | 52.3% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 65.8% |
| LMArena Hard Prompts | — | 1365 |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 15.5% |
| BIG-Bench Hard | — | 87.5% |
| ForecastBench | — | 59.1 |
| HellaSwag | — | 88.9% |
| LiveBench | — | 66.9% |
| PIQA | — | 84.7% |
| WinoGrande | — | 85.2% |

## Math

- Claude 2: 8.7 (#314)
- DeepSeek-V3: 30.4 (#208)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 37.8% |
| MATH Level 5 | 11.7% | 75.5% |
| Omni-MATH | — | 40.3% |
| LiveBench Math | — | 73.5% |
| LMArena Math | — | 1373 |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Claude 2: 17.0 (#282)
- DeepSeek-V3: 37.5 (#147)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| GPQA Diamond | 34.7% | 67.6% |
| MMLU | 78.5% | 87.2% |
| TriviaQA | 87.5% | 82.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 26.1% |
| Vectara Hallucination Rate | — | 6.1% |
| GPQA (HELM) | — | 53.8% |
| LMArena Expert | — | 1352 |
| ARC (AI2) Challenge | — | 95.3% |

## Multilingual

- Claude 2: —
- DeepSeek-V3: 48.8 (#138)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| LMArena Non-English | — | 1358 |
| LMArena Chinese | — | 1390 |
| LMArena French | — | 1386 |
| LMArena German | — | 1374 |
| LMArena Japanese | — | 1333 |
| LMArena Korean | — | 1321 |
| LMArena Russian | — | 1372 |
| LMArena Spanish | — | 1358 |

## Instruction Following

- Claude 2: —
- DeepSeek-V3: 73.0 (#125)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| LiveBench Instruction Following | — | 81.5% |
| IFEval | — | 83.2% |
| LMArena Instruction Following | — | 1345 |

## Long Context

- Claude 2: —
- DeepSeek-V3: 34.0 (#248)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| Fiction.LiveBench | — | 50% |
| LMArena Longer Query | — | 1353 |

## Writing & Preference

- Claude 2: —
- DeepSeek-V3: 57.6 (#124)

| Benchmark | Claude 2 | DeepSeek-V3 |
|---|---|---|
| LMArena Text | — | 1375 |
| LMArena Creative Writing | — | 1364 |
| Short-Story Creative Writing | — | 77% |
| EQ-Bench Creative Writing | — | 1472 |
| WildBench | — | 83% |
| LMArena Multi-Turn | — | 1389 |
| LiveBench Language | — | 49.1% |

## FAQ

### Is Claude 2 better than DeepSeek-V3?

DeepSeek-V3 is the stronger model overall, scoring 39.2 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and DeepSeek-V3 share?

8 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and DeepSeek-V3 has 60.