Model comparison
DBRX vs Qwen1.5-72B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. DBRX scores higher in 2 categories and Qwen1.5-72B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 33.2 to 24.3.
Side by side
| DBRX | Qwen1.5-72B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 30.8 |
| Released | 2024-03-27 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Qwen1.5-72B: 31.9 (#277)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1132 | 1165 |
| HumanEval+ | 70.1% | 59.1% |
| MBPP+ | 55.8% | 61.6% |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
Reasoning Too close to call
DBRX: 21.4 (#222), Qwen1.5-72B: 22.2 (#203)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1148 |
Math Qwen1.5-72B leads
DBRX: 24.3 (#269), Qwen1.5-72B: 33.2 (#205)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1145 | 1164 |
| MATH Level 5 | 11.7% | — |
Knowledge DBRX leads
DBRX: 14.9 (#294), Qwen1.5-72B: 11.5 (#300)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 32.9% | 28.8% |
| LMArena Expert | 1076 | 1136 |
Multilingual Qwen1.5-72B leads
DBRX: 29.3 (#268), Qwen1.5-72B: 33.2 (#253)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1071 | 1135 |
| LMArena Chinese | 1068 | 1186 |
| LMArena French | 1096 | 1159 |
| LMArena German | 1057 | 1084 |
| LMArena Japanese | 990 | 1061 |
| LMArena Korean | 993 | 1050 |
| LMArena Russian | 1078 | 1104 |
| LMArena Spanish | 1064 | 1110 |
Instruction Following Qwen1.5-72B leads
DBRX: 57.5 (#270), Qwen1.5-72B: 59.3 (#256)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1141 |
Long Context Qwen1.5-72B leads
DBRX: 33.7 (#258), Qwen1.5-72B: 35.1 (#243)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1112 | 1157 |
Writing & Preference Qwen1.5-72B leads
DBRX: 33.6 (#275), Qwen1.5-72B: 37.3 (#258)
| Benchmark | DBRX | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1119 | 1166 |
| LMArena Creative Writing | 1104 | 1137 |
| LMArena Multi-Turn | 1111 | 1160 |
Frequently asked questions
Is DBRX better than Qwen1.5-72B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is DBRX or Qwen1.5-72B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 31.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen1.5-72B share?
20 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen1.5-72B has 22.