Model comparison
DBRX vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 29.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Qwen3.5 35B-A3B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 83.5% for Qwen3.5 35B-A3B.
Side by side
| DBRX | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 42.0 |
| Released | 2024-03-27 | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 21 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1132 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Qwen3.5 35B-A3B leads
DBRX: 21.4 (#222), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1400 |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
Math Qwen3.5 35B-A3B leads
DBRX: 24.3 (#269), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1145 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen3.5 35B-A3B leads
DBRX: 14.9 (#294), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 32.9% | 83.5% |
| LMArena Expert | 1076 | 1408 |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Qwen3.5 35B-A3B leads
DBRX: 29.3 (#268), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1071 | 1378 |
| LMArena Chinese | 1068 | 1457 |
| LMArena French | 1096 | 1412 |
| LMArena German | 1057 | 1367 |
| LMArena Japanese | 990 | 1325 |
| LMArena Korean | 993 | 1356 |
| LMArena Russian | 1078 | 1376 |
| LMArena Spanish | 1064 | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
DBRX: 57.5 (#270), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1379 |
Long Context Qwen3.5 35B-A3B leads
DBRX: 33.7 (#258), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1112 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
DBRX: 33.6 (#275), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | DBRX | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1119 | 1395 |
| LMArena Creative Writing | 1104 | 1346 |
| LMArena Multi-Turn | 1111 | 1390 |
Frequently asked questions
Is DBRX better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 29.4 on the Noometry Index.
Is DBRX or Qwen3.5 35B-A3B better for coding?
They score almost the same on coding (32.9 vs 33.8); test both on your own repository before choosing.
How many benchmarks do DBRX and Qwen3.5 35B-A3B share?
18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3.5 35B-A3B has 28.