Model comparison
DBRX vs Qwen1.5 4b Chat
DBRX and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.4 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. DBRX scores higher in 6 categories and Qwen1.5 4b Chat in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5 4b Chat leads 26.7 to 14.9.
Side by side
| DBRX | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 28.8 |
| Released | 2024-03-27 | — |
| 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 DBRX leads
DBRX: 32.9 (#266), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1132 | 999 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1113 | 976 |
Math Qwen1.5 4b Chat leads
DBRX: 24.3 (#269), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1145 | 1026 |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen1.5 4b Chat leads
DBRX: 14.9 (#294), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1076 | 980 |
| GPQA Diamond | 32.9% | — |
Multilingual DBRX leads
DBRX: 29.3 (#268), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1071 | 979 |
| LMArena Chinese | 1068 | 1024 |
| LMArena German | 1057 | 902 |
| LMArena Russian | 1078 | 952 |
| LMArena French | 1096 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1112 | 978 |
Long Context DBRX leads
DBRX: 33.7 (#258), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1112 | 988 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | DBRX | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1119 | 997 |
| LMArena Creative Writing | 1104 | 969 |
| LMArena Multi-Turn | 1111 | 977 |
Frequently asked questions
Is DBRX better than Qwen1.5 4b Chat?
DBRX and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.4 vs 28.8), so choose on price, context window or the category you care about most.
Is DBRX or Qwen1.5 4b Chat better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 29.1 in the Noometry coding category.
How many benchmarks do DBRX and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen1.5 4b Chat has 13.