Model comparison
Claude 2.1 vs DeepSeek LLM 67B
Claude 2.1 and DeepSeek LLM 67B score almost the same on the Noometry Index (25.2 vs 24.9), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. Claude 2.1 scores higher in 3 categories and DeepSeek LLM 67B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 2.1 leads 15.4 to 7.0.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 24.6% for DeepSeek LLM 67B.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.2 | 24.9 |
| Released | 2023-11-21 | 2023-11-29 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
Claude 2.1: 26.2 (#327), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1096 |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| Epoch Capabilities Index | 119.27 | 110.5 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1070 |
| DTBench | 51% | — |
| ForecastBench | 54.2 | — |
Math Claude 2.1 leads
Claude 2.1: 10.2 (#315), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 0.8% |
| LMArena Math | — | 1108 |
| MATH Level 5 | — | 6.4% |
Knowledge Claude 2.1 leads
Claude 2.1: 15.4 (#292), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | 33% | 24.6% |
| MMLU | 73.5% | — |
Multilingual Not comparable
Claude 2.1: —, DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | — | 1073 |
| LMArena Chinese | — | 1132 |
Instruction Following Not comparable
Claude 2.1: —, DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | — | 1079 |
Long Context Not comparable
Claude 2.1: —, DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |
Writing & Preference Not comparable
Claude 2.1: —, DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Claude 2.1 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | — | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |
Frequently asked questions
Is Claude 2.1 better than DeepSeek LLM 67B?
Claude 2.1 and DeepSeek LLM 67B score almost the same on the Noometry Index (25.2 vs 24.9), so choose on price, context window or the category you care about most.
Is Claude 2.1 or DeepSeek LLM 67B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and DeepSeek LLM 67B share?
3 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and DeepSeek LLM 67B has 15.