Model comparison
Qwen-14B vs Qwen1.5-7B
Qwen-14B and Qwen1.5-7B score almost the same on the Noometry Index (31.4 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Qwen-14B scores higher in 0 categories and Qwen1.5-7B in 7 categories; 4 gaps are clear of the uncertainty.
Side by side
| Qwen-14B | Qwen1.5-7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.4 | 31.4 |
| Released | 2023-09-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-7B leads
Qwen-14B: 31.2 (#288), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1071 | 1107 |
Reasoning Too close to call
Qwen-14B: 19.6 (#257), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1065 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Too close to call
Qwen-14B: 31.2 (#227), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1068 | 1080 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen1.5-7B: 28.7 (#243)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| MMLU | 66.3% | 62.6% |
| LMArena Expert | — | 1055 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
Multilingual Too close to call
Qwen-14B: 27.5 (#275), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1041 | 1058 |
| LMArena Chinese | 1077 | 1141 |
| LMArena Russian | — | 1006 |
Instruction Following Qwen1.5-7B leads
Qwen-14B: 52.4 (#289), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1058 |
Long Context Qwen1.5-7B leads
Qwen-14B: 31.3 (#280), Qwen1.5-7B: 33.1 (#266)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1028 | 1090 |
Writing & Preference Qwen1.5-7B leads
Qwen-14B: 27.6 (#299), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Qwen-14B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1051 | 1083 |
| LMArena Creative Writing | 1028 | 1035 |
| LMArena Multi-Turn | 1022 | 1062 |
Frequently asked questions
Is Qwen-14B better than Qwen1.5-7B?
Qwen-14B and Qwen1.5-7B score almost the same on the Noometry Index (31.4 vs 31.4), so choose on price, context window or the category you care about most.
Is Qwen-14B or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen1.5-7B share?
11 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen1.5-7B has 13.