# DBRX vs Qwen3-4B

> Qwen3-4B is the stronger model overall, scoring 31.9 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-qwen3-4b
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DBRX scores higher in 1 category and Qwen3-4B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 52.3% for Qwen3-4B.

## Snapshot

| | DBRX | Qwen3-4B |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 29.4 | 31.9 |
| Rank | 311 | 264 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DBRX: 32.9 (#266)
- Qwen3-4B: —

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| LMArena Coding | 1132 | — |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- Qwen3-4B: 27.6 (#100)

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |

## Reasoning

- DBRX: 21.4 (#222)
- Qwen3-4B: 19.2 (#268)

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1113 | — |

## Math

- DBRX: 24.3 (#269)
- Qwen3-4B: 29.7 (#240)

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| LMArena Math | 1145 | — |
| MATH Level 5 | 11.7% | — |

## Knowledge

- DBRX: 14.9 (#294)
- Qwen3-4B: 33.0 (#208)

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 32.9% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1076 | — |

## Multilingual

- DBRX: 29.3 (#268)
- Qwen3-4B: —

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1071 | — |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |

## Instruction Following

- DBRX: 57.5 (#270)
- Qwen3-4B: —

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1112 | — |

## Long Context

- DBRX: 33.7 (#258)
- Qwen3-4B: —

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1112 | — |

## Writing & Preference

- DBRX: 33.6 (#275)
- Qwen3-4B: —

| Benchmark | DBRX | Qwen3-4B |
|---|---|---|
| LMArena Text | 1119 | — |
| LMArena Creative Writing | 1104 | — |
| LMArena Multi-Turn | 1111 | — |

## FAQ

### Is DBRX better than Qwen3-4B?

Qwen3-4B is the stronger model overall, scoring 31.9 to 29.4 on the Noometry Index.

### How many benchmarks do DBRX and Qwen3-4B share?

1 benchmark has published results for both models. DBRX has 21 scored results on Noometry and Qwen3-4B has 6.