Model comparison
DBRX vs Qwen2.5 14B Instruct
DBRX has enough public results to be ranked (#311); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen2.5 14B Instruct leads 37.7 to 32.9.
Side by side
| DBRX | Qwen2.5 14B Instruct | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 38.7 |
| Released | 2024-03-27 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 21 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 14B Instruct leads
DBRX: 32.9 (#266), Qwen2.5 14B Instruct: 37.7 (#191)
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 39.8% |
| LMArena Coding | 1132 | — |
| BigCodeBench Complete | — | 52.2% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Not comparable
DBRX: 21.4 (#222), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | — |
Math Not comparable
DBRX: 24.3 (#269), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Math | 1145 | — |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#294), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
| MMLU | — | 79.9% |
Multilingual Not comparable
DBRX: 29.3 (#268), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Non-English | 1071 | — |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Not comparable
DBRX: 57.5 (#270), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | — |
Long Context Not comparable
DBRX: 33.7 (#258), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference Not comparable
DBRX: 33.6 (#275), Qwen2.5 14B Instruct: —
| Benchmark | DBRX | Qwen2.5 14B Instruct |
|---|---|---|
| LMArena Text | 1119 | — |
| LMArena Creative Writing | 1104 | — |
| LMArena Multi-Turn | 1111 | — |
Frequently asked questions
Is DBRX better than Qwen2.5 14B Instruct?
DBRX has enough public results to be ranked (#311); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
Is DBRX or Qwen2.5 14B Instruct better for coding?
Qwen2.5 14B Instruct scores higher on coding benchmarks: 37.7 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen2.5 14B Instruct share?
0 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen2.5 14B Instruct has 3.