Model comparison
DeepSeek-V3.1 vs Llama2 70b Steerlm Chat
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1 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 writing & preference, where DeepSeek-V3.1 leads 60.3 to 31.6.
Side by side
| DeepSeek-V3.1 | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 42.8 | 31.8 |
| Released | 2025-08-21 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1417 | 1025 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1047 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1420 | 1072 |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), Llama2 70b Steerlm Chat: —
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1400 | 1063 |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1400 | 1060 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1422 | 998 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | DeepSeek-V3.1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1420 | 1098 |
| LMArena Creative Writing | 1401 | 1091 |
| LMArena Multi-Turn | 1408 | 1058 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Llama2 70b Steerlm Chat?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.8 on the Noometry Index.
Is DeepSeek-V3.1 or Llama2 70b Steerlm Chat better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 29.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Llama2 70b Steerlm Chat has 9.