# Claude 2 vs DeepSeek LLM 67B

> Claude 2 and DeepSeek LLM 67B score almost the same on the Noometry Index (25.0 vs 24.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-2-vs-deepseek-llm-67b
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Claude 2 scores higher in 3 categories and DeepSeek LLM 67B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 2 leads 16.9 to 7.0.
- The biggest single-benchmark swing is GPQA Diamond: 34.7% for Claude 2 and 24.6% for DeepSeek LLM 67B.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.0 | 24.9 |
| Rank | 346 | 347 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- DeepSeek LLM 67B: 31.9 (#278)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | — | 1096 |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 21.7 (#216)
- DeepSeek LLM 67B: 16.5 (#304)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 110.5 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1070 |
| DTBench | 51.9% | — |

## Math

- Claude 2: 9.3 (#320)
- DeepSeek LLM 67B: 8.7 (#324)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 0.8% |
| MATH Level 5 | 11.7% | 6.4% |
| LMArena Math | — | 1108 |

## Knowledge

- Claude 2: 16.9 (#287)
- DeepSeek LLM 67B: 7.0 (#313)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | 34.7% | 24.6% |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multilingual

- Claude 2: —
- DeepSeek LLM 67B: 29.4 (#267)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | — | 1073 |
| LMArena Chinese | — | 1132 |

## Instruction Following

- Claude 2: —
- DeepSeek LLM 67B: 55.4 (#277)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | — | 1079 |

## Long Context

- Claude 2: —
- DeepSeek LLM 67B: 33.1 (#265)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |

## Writing & Preference

- Claude 2: —
- DeepSeek LLM 67B: 31.6 (#282)

| Benchmark | Claude 2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | — | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |

## FAQ

### Is Claude 2 better than DeepSeek LLM 67B?

Claude 2 and DeepSeek LLM 67B score almost the same on the Noometry Index (25.0 vs 24.9), so choose on price, context window or the category you care about most.

### How many benchmarks do Claude 2 and DeepSeek LLM 67B share?

4 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and DeepSeek LLM 67B has 15.