Model comparison
DBRX vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 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-Next 80B-A3B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.8 to 14.9.
Side by side
| DBRX | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 43.0 |
| Released | 2024-03-27 | 2025-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2 |
| Results tracked | 21 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
DBRX: 32.9 (#266), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1132 | 1440 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
DBRX: 21.4 (#222), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
Math Qwen3-Next 80B-A3B Instruct leads
DBRX: 24.3 (#269), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1145 | 1440 |
| Omni-MATH | — | 46.7% |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen3-Next 80B-A3B Instruct leads
DBRX: 14.9 (#294), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1076 | 1417 |
| GPQA Diamond | 32.9% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multilingual Qwen3-Next 80B-A3B Instruct leads
DBRX: 29.3 (#268), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1071 | 1407 |
| LMArena Chinese | 1068 | 1460 |
| LMArena French | 1096 | 1413 |
| LMArena German | 1057 | 1417 |
| LMArena Japanese | 990 | 1395 |
| LMArena Korean | 993 | 1364 |
| LMArena Russian | 1078 | 1404 |
| LMArena Spanish | 1064 | 1435 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
DBRX: 57.5 (#270), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | 1389 |
| IFEval | — | 81% |
Long Context Qwen3-Next 80B-A3B Instruct leads
DBRX: 33.7 (#258), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
DBRX: 33.6 (#275), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | DBRX | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1119 | 1417 |
| LMArena Creative Writing | 1104 | 1334 |
| LMArena Multi-Turn | 1111 | 1416 |
| WildBench | — | 80.7% |
Frequently asked questions
Is DBRX better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 29.4 on the Noometry Index.
Is DBRX or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen3-Next 80B-A3B Instruct share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.