Model comparison
Claude 3 Sonnet vs DeepSeek LLM 67B
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. Claude 3 Sonnet scores higher in 7 categories and DeepSeek LLM 67B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3 Sonnet leads 21.1 to 7.0.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 24.6% for DeepSeek LLM 67B.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 29.0 | 24.9 |
| Released | 2024-02-29 | 2023-11-29 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
Claude 3 Sonnet: 29.6 (#302), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1223 | 1096 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1070 |
| Epoch Capabilities Index | 120.7 | 110.5 |
| Chess Puzzles | — | 0% |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |
Math Claude 3 Sonnet leads
Claude 3 Sonnet: 10.7 (#310), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 0.8% |
| LMArena Math | 1213 | 1108 |
| MATH Level 5 | 18.2% | 6.4% |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#276), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | 40.6% | 24.6% |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), DeepSeek LLM 67B: —
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1205 | 1073 |
| LMArena Chinese | 1189 | 1132 |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1079 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#228), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1211 | 1092 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Claude 3 Sonnet | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1218 | 1105 |
| LMArena Creative Writing | 1186 | 1067 |
| LMArena Multi-Turn | 1227 | 1082 |
Frequently asked questions
Is Claude 3 Sonnet better than DeepSeek LLM 67B?
Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.9 on the Noometry Index.
Is Claude 3 Sonnet or DeepSeek LLM 67B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and DeepSeek LLM 67B share?
14 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek LLM 67B has 15.