Model comparison
DBRX vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 29.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. DBRX scores higher in 2 categories and Qwen Max in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 14.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 67.2% for Qwen Max.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Qwen Max | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 34.7 |
| Released | 2024-03-27 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Qwen Max: 30.7 (#292)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Coding | 1132 | 1288 |
| Aider Polyglot | — | 21.8% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Qwen Max leads
DBRX: 21.4 (#222), Qwen Max: 25.1 (#151)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1269 |
Math DBRX leads
DBRX: 24.3 (#269), Qwen Max: 22.3 (#276)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Math | 1145 | 1275 |
| MATH Level 5 | 11.7% | 67.2% |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
DBRX: 14.9 (#294), Qwen Max: 30.3 (#228)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| GPQA Diamond | 32.9% | 56.1% |
| LMArena Expert | 1076 | 1248 |
Multilingual Qwen Max leads
DBRX: 29.3 (#268), Qwen Max: 41.8 (#202)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Non-English | 1071 | 1263 |
| LMArena Chinese | 1068 | 1254 |
| LMArena French | 1096 | 1330 |
| LMArena German | 1057 | 1254 |
| LMArena Japanese | 990 | 1205 |
| LMArena Korean | 993 | 1142 |
| LMArena Russian | 1078 | 1274 |
| LMArena Spanish | 1064 | 1290 |
Instruction Following Qwen Max leads
DBRX: 57.5 (#270), Qwen Max: 66.5 (#208)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1112 | 1262 |
Long Context Qwen Max leads
DBRX: 33.7 (#258), Qwen Max: 39.4 (#180)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1112 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
DBRX: 33.6 (#275), Qwen Max: 47.8 (#205)
| Benchmark | DBRX | Qwen Max |
|---|---|---|
| LMArena Text | 1119 | 1282 |
| LMArena Creative Writing | 1104 | 1248 |
| LMArena Multi-Turn | 1111 | 1277 |
Frequently asked questions
Is DBRX better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 29.4 on the Noometry Index.
Is DBRX or Qwen Max better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 30.7 in the Noometry coding category.
How many benchmarks do DBRX and Qwen Max share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen Max has 23.