Model comparison
DBRX vs Qwen2-72B
DBRX and Qwen2-72B score almost the same on the Noometry Index (29.4 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. DBRX scores higher in 1 category and Qwen2-72B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 39.1% for Qwen2-72B.
Side by side
| DBRX | Qwen2-72B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 30.0 |
| Released | 2024-03-27 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Qwen2-72B: 29.1 (#310)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1132 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Qwen2-72B: 17.0 (#146)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
DBRX: 21.4 (#222), Qwen2-72B: 23.2 (#181)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Qwen2-72B leads
DBRX: 24.3 (#269), Qwen2-72B: 30.2 (#236)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Math | 1145 | 1235 |
| MATH Level 5 | 11.7% | 39.1% |
Knowledge Qwen2-72B leads
DBRX: 14.9 (#294), Qwen2-72B: 21.2 (#275)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 32.9% | 40.8% |
| LMArena Expert | 1076 | 1171 |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
DBRX: 29.3 (#268), Qwen2-72B: 35.9 (#244)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1071 | 1176 |
| LMArena Chinese | 1068 | 1240 |
| LMArena French | 1096 | 1170 |
| LMArena German | 1057 | 1151 |
| LMArena Japanese | 990 | 1111 |
| LMArena Korean | 993 | 1083 |
| LMArena Russian | 1078 | 1169 |
| LMArena Spanish | 1064 | 1169 |
Instruction Following Qwen2-72B leads
DBRX: 57.5 (#270), Qwen2-72B: 61.7 (#241)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1181 |
Long Context Qwen2-72B leads
DBRX: 33.7 (#258), Qwen2-72B: 36.1 (#235)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1112 | 1192 |
Writing & Preference Qwen2-72B leads
DBRX: 33.6 (#275), Qwen2-72B: 40.8 (#241)
| Benchmark | DBRX | Qwen2-72B |
|---|---|---|
| LMArena Text | 1119 | 1203 |
| LMArena Creative Writing | 1104 | 1181 |
| LMArena Multi-Turn | 1111 | 1196 |
Frequently asked questions
Is DBRX better than Qwen2-72B?
DBRX and Qwen2-72B score almost the same on the Noometry Index (29.4 vs 30.0), so choose on price, context window or the category you care about most.
Is DBRX or Qwen2-72B 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 Qwen2-72B share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen2-72B has 26.