Model comparison
DBRX vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and Qwen1.5-110B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-110B leads 31.2 to 14.9.
Side by side
| DBRX | Qwen1.5-110B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 34.2 |
| Released | 2024-03-27 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Qwen1.5-110B: 33.0 (#264)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1132 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Qwen1.5-110B leads
DBRX: 21.4 (#222), Qwen1.5-110B: 22.7 (#189)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1168 |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
DBRX: 24.3 (#269), Qwen1.5-110B: 33.7 (#201)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1145 | 1185 |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen1.5-110B leads
DBRX: 14.9 (#294), Qwen1.5-110B: 31.2 (#219)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1076 | 1144 |
| GPQA Diamond | 32.9% | — |
Multilingual Qwen1.5-110B leads
DBRX: 29.3 (#268), Qwen1.5-110B: 33.6 (#250)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1071 | 1142 |
| LMArena Chinese | 1068 | 1206 |
| LMArena French | 1096 | 1151 |
| LMArena German | 1057 | 1123 |
| LMArena Japanese | 990 | 1074 |
| LMArena Korean | 993 | 1044 |
| LMArena Russian | 1078 | 1118 |
| LMArena Spanish | 1064 | 1142 |
Instruction Following Qwen1.5-110B leads
DBRX: 57.5 (#270), Qwen1.5-110B: 60.3 (#252)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1158 |
Long Context Qwen1.5-110B leads
DBRX: 33.7 (#258), Qwen1.5-110B: 35.1 (#242)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1112 | 1157 |
Writing & Preference Qwen1.5-110B leads
DBRX: 33.6 (#275), Qwen1.5-110B: 38.0 (#255)
| Benchmark | DBRX | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1119 | 1175 |
| LMArena Creative Writing | 1104 | 1148 |
| LMArena Multi-Turn | 1111 | 1160 |
Frequently asked questions
Is DBRX better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.4 on the Noometry Index.
Is DBRX or Qwen1.5-110B better for coding?
They score almost the same on coding (32.9 vs 33.0); test both on your own repository before choosing.
How many benchmarks do DBRX and Qwen1.5-110B share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen1.5-110B has 20.