Model comparison
DBRX vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. DBRX scores higher in 6 categories and Qwen1.5-7B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.7 to 14.9.
Side by side
| DBRX | Qwen1.5-7B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 31.4 |
| Released | 2024-03-27 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Qwen1.5-7B: 32.2 (#276)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1132 | 1107 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Qwen1.5-7B: 20.4 (#240)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1065 |
Math Qwen1.5-7B leads
DBRX: 24.3 (#269), Qwen1.5-7B: 31.4 (#224)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1145 | 1080 |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen1.5-7B leads
DBRX: 14.9 (#294), Qwen1.5-7B: 28.7 (#243)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1076 | 1055 |
| GPQA Diamond | 32.9% | — |
| MMLU | — | 62.6% |
Multilingual Too close to call
DBRX: 29.3 (#268), Qwen1.5-7B: 28.5 (#271)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1071 | 1058 |
| LMArena Chinese | 1068 | 1141 |
| LMArena Russian | 1078 | 1006 |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Qwen1.5-7B: 54.1 (#281)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1058 |
Long Context Too close to call
DBRX: 33.7 (#258), Qwen1.5-7B: 33.1 (#266)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1112 | 1090 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Qwen1.5-7B: 29.6 (#293)
| Benchmark | DBRX | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1119 | 1083 |
| LMArena Creative Writing | 1104 | 1035 |
| LMArena Multi-Turn | 1111 | 1062 |
Frequently asked questions
Is DBRX better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.
Is DBRX or Qwen1.5-7B better for coding?
They score almost the same on coding (32.9 vs 32.2); test both on your own repository before choosing.
How many benchmarks do DBRX and Qwen1.5-7B share?
12 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen1.5-7B has 13.