Model comparison
DBRX vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 29.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. DBRX scores higher in 1 category and Qwen1.5-14B in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-14B leads 29.8 to 14.9.
Side by side
| DBRX | Qwen1.5-14B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 32.7 |
| Released | 2024-03-27 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Qwen1.5-14B: 33.1 (#263)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1132 | 1138 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Too close to call
DBRX: 21.4 (#222), Qwen1.5-14B: 21.4 (#223)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1113 |
Math Qwen1.5-14B leads
DBRX: 24.3 (#269), Qwen1.5-14B: 32.4 (#215)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1145 | 1125 |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen1.5-14B leads
DBRX: 14.9 (#294), Qwen1.5-14B: 29.8 (#232)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1076 | 1094 |
| GPQA Diamond | 32.9% | — |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
DBRX: 29.3 (#268), Qwen1.5-14B: 30.7 (#262)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1071 | 1095 |
| LMArena Chinese | 1068 | 1147 |
| LMArena French | 1096 | 1116 |
| LMArena German | 1057 | 1043 |
| LMArena Japanese | 990 | 1019 |
| LMArena Russian | 1078 | 1046 |
| LMArena Spanish | 1064 | 1085 |
| LMArena Korean | 993 | — |
Instruction Following Too close to call
DBRX: 57.5 (#270), Qwen1.5-14B: 56.8 (#271)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1102 |
Long Context Too close to call
DBRX: 33.7 (#258), Qwen1.5-14B: 33.7 (#257)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1112 | 1113 |
Writing & Preference Too close to call
DBRX: 33.6 (#275), Qwen1.5-14B: 33.6 (#276)
| Benchmark | DBRX | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1119 | 1128 |
| LMArena Creative Writing | 1104 | 1091 |
| LMArena Multi-Turn | 1111 | 1110 |
Frequently asked questions
Is DBRX better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 29.4 on the Noometry Index.
Is DBRX or Qwen1.5-14B better for coding?
They score almost the same on coding (32.9 vs 33.1); test both on your own repository before choosing.
How many benchmarks do DBRX and Qwen1.5-14B share?
16 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen1.5-14B has 17.