Model comparison
Llama2 70b Steerlm Chat vs Qwen-14B
Llama2 70b Steerlm Chat and Qwen-14B score almost the same on the Noometry Index (31.8 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 9 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Llama2 70b Steerlm Chat scores higher in 5 categories and Qwen-14B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama2 70b Steerlm Chat leads 31.6 to 27.6.
Side by side
| Llama2 70b Steerlm Chat | Qwen-14B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 31.8 | 31.4 |
| Released | — | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Llama2 70b Steerlm Chat: 29.9 (#300), Qwen-14B: 31.2 (#288)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Coding | 1025 | 1071 |
Reasoning Too close to call
Llama2 70b Steerlm Chat: 20.0 (#246), Qwen-14B: 19.6 (#257)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Too close to call
Llama2 70b Steerlm Chat: 31.3 (#226), Qwen-14B: 31.2 (#227)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Math | 1072 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Qwen-14B: —
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 28.8 (#270), Qwen-14B: 27.5 (#275)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1063 | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 54.2 (#279), Qwen-14B: 52.4 (#289)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1031 |
Long Context Too close to call
Llama2 70b Steerlm Chat: 30.4 (#288), Qwen-14B: 31.3 (#280)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 998 | 1028 |
Writing & Preference Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 31.6 (#283), Qwen-14B: 27.6 (#299)
| Benchmark | Llama2 70b Steerlm Chat | Qwen-14B |
|---|---|---|
| LMArena Text | 1098 | 1051 |
| LMArena Creative Writing | 1091 | 1028 |
| LMArena Multi-Turn | 1058 | 1022 |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Qwen-14B?
Llama2 70b Steerlm Chat and Qwen-14B score almost the same on the Noometry Index (31.8 vs 31.4), so choose on price, context window or the category you care about most.
Is Llama2 70b Steerlm Chat or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Qwen-14B share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Qwen-14B has 18.