Model comparison
Deepseek Coder v2 vs DeepSeek LLM 67B
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and DeepSeek LLM 67B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 8.7.
Side by side
| Deepseek Coder v2 | DeepSeek LLM 67B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 35.9 | 24.9 |
| Released | 2024-06-17 | 2023-11-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1251 | 1096 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1070 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 110.5 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1241 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| MATH Level 5 | — | 6.4% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1182 | 1073 |
| LMArena Chinese | 1201 | 1132 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.7 (#242), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1079 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#224), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1219 | 1092 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Deepseek Coder v2 | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1191 | 1105 |
| LMArena Creative Writing | 1120 | 1067 |
| LMArena Multi-Turn | 1177 | 1082 |
Frequently asked questions
Is Deepseek Coder v2 better than DeepSeek LLM 67B?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 24.9 on the Noometry Index.
Is Deepseek Coder v2 or DeepSeek LLM 67B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 31.9 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and DeepSeek LLM 67B share?
10 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek LLM 67B has 15.