# DBRX vs Qwen3-30B-A3B

> Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DBRX scores higher in 1 category and Qwen3-30B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 70.1% for Qwen3-30B-A3B.

## Snapshot

| | DBRX | Qwen3-30B-A3B |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 38.9 |
| Rank | 311 | 179 |
| Context | — | 41K |
| Input $/M | — | $0.12 |
| Output $/M | — | $0.50 |
| Weights | Open | Open |

## Coding

- DBRX: 32.9 (#266)
- Qwen3-30B-A3B: 37.5 (#194)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1132 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- Qwen3-30B-A3B: 29.8 (#82)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |

## Reasoning

- DBRX: 21.4 (#222)
- Qwen3-30B-A3B: 22.2 (#204)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |

## Math

- DBRX: 24.3 (#269)
- Qwen3-30B-A3B: 37.4 (#157)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1145 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| MATH Level 5 | 11.7% | — |

## Knowledge

- DBRX: 14.9 (#294)
- Qwen3-30B-A3B: 41.8 (#105)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 32.9% | 70.1% |
| LMArena Expert | 1076 | 1396 |
| Confabulations | — | 12.3% |

## Multilingual

- DBRX: 29.3 (#268)
- Qwen3-30B-A3B: 49.5 (#132)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1071 | 1372 |
| LMArena Chinese | 1068 | 1433 |
| LMArena French | 1096 | 1418 |
| LMArena German | 1057 | 1380 |
| LMArena Japanese | 990 | 1337 |
| LMArena Korean | 993 | 1331 |
| LMArena Russian | 1078 | 1370 |
| LMArena Spanish | 1064 | 1404 |

## Instruction Following

- DBRX: 57.5 (#270)
- Qwen3-30B-A3B: 72.0 (#142)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1363 |

## Long Context

- DBRX: 33.7 (#258)
- Qwen3-30B-A3B: 31.0 (#283)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1112 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- DBRX: 33.6 (#275)
- Qwen3-30B-A3B: 55.6 (#143)

| Benchmark | DBRX | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1119 | 1384 |
| LMArena Creative Writing | 1104 | 1317 |
| LMArena Multi-Turn | 1111 | 1378 |
| Short-Story Creative Writing | — | 75.3% |

## FAQ

### Is DBRX better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.

### Is DBRX or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 32.9 in the Noometry coding category.

### How many benchmarks do DBRX and Qwen3-30B-A3B share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3-30B-A3B has 32.