Model comparison
DBRX vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 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 Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 24.3.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 92.7% for Qwen3.8 Max.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Qwen3.8 Max | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 56.8 |
| Released | 2024-03-27 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 21 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
DBRX: 32.9 (#266), Qwen3.8 Max: 53.5 (#29)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1132 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
DBRX: 21.4 (#222), Qwen3.8 Max: 54.4 (#26)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
DBRX: 24.3 (#269), Qwen3.8 Max: 73.2 (#20)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1145 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| MATH Level 5 | 11.7% | — |
Knowledge Qwen3.8 Max leads
DBRX: 14.9 (#294), Qwen3.8 Max: 61.7 (#27)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 32.9% | 92.7% |
| LMArena Expert | 1076 | 1507 |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
DBRX: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
DBRX: 29.3 (#268), Qwen3.8 Max: 56.7 (#18)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1071 | 1472 |
| LMArena Chinese | 1068 | 1538 |
| LMArena French | 1096 | 1503 |
| LMArena German | 1057 | 1483 |
| LMArena Japanese | 990 | 1467 |
| LMArena Korean | 993 | 1461 |
| LMArena Russian | 1078 | 1481 |
| LMArena Spanish | 1064 | 1492 |
Instruction Following Qwen3.8 Max leads
DBRX: 57.5 (#270), Qwen3.8 Max: 77.6 (#17)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1112 | 1479 |
Long Context Qwen3.8 Max leads
DBRX: 33.7 (#258), Qwen3.8 Max: 45.6 (#31)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1112 | 1489 |
Writing & Preference Qwen3.8 Max leads
DBRX: 33.6 (#275), Qwen3.8 Max: 67.1 (#30)
| Benchmark | DBRX | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1119 | 1483 |
| LMArena Creative Writing | 1104 | 1479 |
| LMArena Multi-Turn | 1111 | 1489 |
Frequently asked questions
Is DBRX better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.4 on the Noometry Index.
Is DBRX or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Qwen3.8 Max share?
18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3.8 Max has 39.