Model comparison
DBRX vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 33.6.
Side by side
| DBRX | Qwen3.8 27B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 46.0 |
| Released | 2024-03-27 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
DBRX: 32.9 (#266), Qwen3.8 27B: 50.5 (#44)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1132 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
DBRX: 21.4 (#222), Qwen3.8 27B: 41.0 (#54)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
DBRX: 24.3 (#269), Qwen3.8 27B: 37.1 (#161)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1145 | 1456 |
| ProofBench | — | 16% |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen3.8 27B leads
DBRX: 14.9 (#294), Qwen3.8 27B: 41.6 (#109)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1076 | 1482 |
| GPQA Diamond | 32.9% | — |
Multimodal Not comparable
DBRX: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
DBRX: 29.3 (#268), Qwen3.8 27B: 53.7 (#60)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1071 | 1430 |
| LMArena Chinese | 1068 | 1504 |
| LMArena French | 1096 | 1465 |
| LMArena German | 1057 | 1438 |
| LMArena Japanese | 990 | 1384 |
| LMArena Korean | 993 | 1393 |
| LMArena Russian | 1078 | 1415 |
| LMArena Spanish | 1064 | 1448 |
Instruction Following Qwen3.8 27B leads
DBRX: 57.5 (#270), Qwen3.8 27B: 75.8 (#53)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1439 |
Long Context Qwen3.8 27B leads
DBRX: 33.7 (#258), Qwen3.8 27B: 44.3 (#70)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1112 | 1450 |
Writing & Preference Qwen3.8 27B leads
DBRX: 33.6 (#275), Qwen3.8 27B: 65.8 (#43)
| Benchmark | DBRX | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1119 | 1441 |
| LMArena Creative Writing | 1104 | 1384 |
| LMArena Multi-Turn | 1111 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is DBRX better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 29.4 on the Noometry Index.
Is DBRX or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen3.8 27B share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3.8 27B has 31.