Model comparison
Qwen-7B vs Qwen1.5-7B
Qwen1.5-7B has enough public results to be ranked (#270); Qwen-7B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both.
Side by side
| Qwen-7B | Qwen1.5-7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | — | 30.8 |
| Released | 2023-09-28 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen-7B: —, Qwen1.5-7B: 31.6 (#271)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | — | 1107 |
Reasoning Not comparable
Qwen-7B: —, Qwen1.5-7B: 19.5 (#237)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | — | 1066 |
| BIG-Bench Hard | 45% | — |
| Epoch Capabilities Index | 106.47 | — |
| LAMBADA | 67.9% | — |
| PIQA | 77.9% | — |
Math Not comparable
Qwen-7B: —, Qwen1.5-7B: 29.0 (#222)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |
| GSM8K | 51.7% | — |
Knowledge Not comparable
Qwen-7B: —, Qwen1.5-7B: 28.2 (#239)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| MMLU | 45% | 62.6% |
| LMArena Expert | — | 1055 |
| ARC (AI2) Challenge | 75.3% | — |
| BoolQ | 76.4% | — |
Multilingual Not comparable
Qwen-7B: —, Qwen1.5-7B: 28.6 (#266)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | — | 1058 |
| LMArena Chinese | — | 1140 |
| LMArena Russian | — | 1006 |
Instruction Following Not comparable
Qwen-7B: —, Qwen1.5-7B: 54.4 (#276)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | — | 1058 |
Long Context Not comparable
Qwen-7B: —, Qwen1.5-7B: 33.1 (#261)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |
Writing & Preference Not comparable
Qwen-7B: —, Qwen1.5-7B: 29.8 (#288)
| Benchmark | Qwen-7B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | — | 1084 |
| LMArena Creative Writing | — | 1035 |
| LMArena Multi-Turn | — | 1061 |
Frequently asked questions
Is Qwen-7B better than Qwen1.5-7B?
Qwen1.5-7B has enough public results to be ranked (#270); Qwen-7B does not yet, so treat this comparison as directional.
How many benchmarks do Qwen-7B and Qwen1.5-7B share?
1 benchmark has published results for both models. Qwen-7B has 8 scored results on Noometry and Qwen1.5-7B has 13.