Model comparison
Llama2 70b Steerlm Chat vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.8 on the Noometry Index.
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 0 categories and Qwen1.5-110B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-110B leads 38.0 to 31.6.
Side by side
| Llama2 70b Steerlm Chat | Qwen1.5-110B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 31.8 | 34.2 |
| Released | — | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 29.9 (#300), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1025 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 20.0 (#246), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1168 |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 31.3 (#226), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1072 | 1185 |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Qwen1.5-110B: 31.2 (#219)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | — | 1144 |
Multilingual Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 28.8 (#270), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1063 | 1142 |
| LMArena Chinese | — | 1206 |
| LMArena French | — | 1151 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Russian | — | 1118 |
| LMArena Spanish | — | 1142 |
Instruction Following Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 54.2 (#279), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1060 | 1158 |
Long Context Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 30.4 (#288), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 998 | 1157 |
Writing & Preference Qwen1.5-110B leads
Llama2 70b Steerlm Chat: 31.6 (#283), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Llama2 70b Steerlm Chat | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1098 | 1175 |
| LMArena Creative Writing | 1091 | 1148 |
| LMArena Multi-Turn | 1058 | 1160 |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.8 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Qwen1.5-110B share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Qwen1.5-110B has 20.