Model comparison
Deepseek Coder v2 vs Llama2 70b Steerlm Chat
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 9 benchmarks with published results for both. Deepseek Coder v2 scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Deepseek Coder v2 leads 38.1 to 29.9.
Side by side
| Deepseek Coder v2 | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 35.9 | 31.8 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 9 |
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), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1251 | 1025 |
| 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), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1047 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1241 | 1072 |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Llama2 70b Steerlm Chat: —
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1182 | 1063 |
| LMArena Chinese | 1201 | — |
| 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), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1180 | 1060 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#224), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1219 | 998 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Deepseek Coder v2 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1191 | 1098 |
| LMArena Creative Writing | 1120 | 1091 |
| LMArena Multi-Turn | 1177 | 1058 |
Frequently asked questions
Is Deepseek Coder v2 better than Llama2 70b Steerlm Chat?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.8 on the Noometry Index.
Is Deepseek Coder v2 or Llama2 70b Steerlm Chat better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 29.9 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Llama2 70b Steerlm Chat has 9.