Model comparison
DeepSeek LLM 67B vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 24.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 9 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 5 categories and Llama2 70b Steerlm Chat in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 8.7.
Side by side
| DeepSeek LLM 67B | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 24.9 | 31.8 |
| Released | 2023-11-29 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1096 | 1025 |
Reasoning Llama2 70b Steerlm Chat leads
DeepSeek LLM 67B: 16.5 (#304), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1047 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Llama2 70b Steerlm Chat leads
DeepSeek LLM 67B: 8.7 (#324), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1108 | 1072 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Not comparable
DeepSeek LLM 67B: 7.0 (#313), Llama2 70b Steerlm Chat: —
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual Too close to call
DeepSeek LLM 67B: 29.4 (#267), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1073 | 1063 |
| LMArena Chinese | 1132 | — |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1079 | 1060 |
Long Context DeepSeek LLM 67B leads
DeepSeek LLM 67B: 33.1 (#265), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1092 | 998 |
Writing & Preference Too close to call
DeepSeek LLM 67B: 31.6 (#282), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | DeepSeek LLM 67B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1105 | 1098 |
| LMArena Creative Writing | 1067 | 1091 |
| LMArena Multi-Turn | 1082 | 1058 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Llama2 70b Steerlm Chat better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 29.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama2 70b Steerlm Chat has 9.