Model comparison
DBRX vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DBRX scores higher in 1 category and Qwen3 32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 65.7% for Qwen3 32B.
Side by side
| DBRX | Qwen3 32B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 39.2 |
| Released | 2024-03-27 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
DBRX: 32.9 (#266), Qwen3 32B: 37.7 (#190)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1132 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Qwen3 32B: 32.6 (#62)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Qwen3 32B: 20.2 (#241)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
DBRX: 24.3 (#269), Qwen3 32B: 39.7 (#99)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Math | 1145 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen3 32B leads
DBRX: 14.9 (#294), Qwen3 32B: 40.0 (#125)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 32.9% | 65.7% |
| LMArena Expert | 1076 | 1362 |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual Qwen3 32B leads
DBRX: 29.3 (#268), Qwen3 32B: 45.6 (#167)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1071 | 1317 |
| LMArena Chinese | 1068 | 1357 |
| LMArena German | 1057 | 1341 |
| LMArena Russian | 1078 | 1311 |
| LMArena French | 1096 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Qwen3 32B leads
DBRX: 57.5 (#270), Qwen3 32B: 68.9 (#179)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1305 |
Long Context Qwen3 32B leads
DBRX: 33.7 (#258), Qwen3 32B: 43.8 (#87)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1112 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
DBRX: 33.6 (#275), Qwen3 32B: 52.9 (#163)
| Benchmark | DBRX | Qwen3 32B |
|---|---|---|
| LMArena Text | 1119 | 1340 |
| LMArena Creative Writing | 1104 | 1297 |
| LMArena Multi-Turn | 1111 | 1331 |
Frequently asked questions
Is DBRX better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.4 on the Noometry Index.
Is DBRX or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen3 32B share?
14 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3 32B has 26.