Model comparison
DBRX vs Gemma 3 4B
DBRX is the stronger model overall, scoring 29.0 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Databricks
GoogleSummary
- They share 13 benchmarks with published results for both. DBRX scores higher in 3 categories and Gemma 3 4B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 4B leads 42.7 to 29.4.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 23.2% for Gemma 3 4B.
Side by side
| DBRX | Gemma 3 4B | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 29.0 | 27.9 |
| Released | 2024-03-27 | 2025-03-12 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
DBRX: 32.3 (#262), Gemma 3 4B: 35.3 (#214)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1132 | 1230 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Gemma 3 4B: 20.7 (#134)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |
Reasoning DBRX leads
DBRX: 20.5 (#218), Gemma 3 4B: 12.7 (#330)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1253 |
| Kagi LLM Benchmark | — | 25.2% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |
Math DBRX leads
DBRX: 22.3 (#265), Gemma 3 4B: 15.8 (#286)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Math | 1145 | 1239 |
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| MATH Level 5 | 11.7% | — |
Knowledge DBRX leads
DBRX: 14.9 (#289), Gemma 3 4B: 11.8 (#294)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | 32.9% | 23.2% |
| LMArena Expert | 1076 | 1223 |
| Vectara Hallucination Rate | — | 6.4% |
Multilingual Gemma 3 4B leads
DBRX: 29.4 (#263), Gemma 3 4B: 42.7 (#189)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1071 | 1273 |
| LMArena German | 1057 | 1281 |
| LMArena Russian | 1078 | 1294 |
| LMArena Chinese | 1068 | — |
| LMArena French | 1095 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Gemma 3 4B leads
DBRX: 57.7 (#265), Gemma 3 4B: 65.4 (#219)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1239 |
Long Context Gemma 3 4B leads
DBRX: 33.7 (#253), Gemma 3 4B: 38.6 (#189)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1112 | 1274 |
Writing & Preference Gemma 3 4B leads
DBRX: 33.7 (#271), Gemma 3 4B: 42.2 (#234)
| Benchmark | DBRX | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1119 | 1291 |
| LMArena Creative Writing | 1104 | 1270 |
| LMArena Multi-Turn | 1111 | 1255 |
| EQ-Bench Creative Writing | — | 1068 |
Frequently asked questions
Is DBRX better than Gemma 3 4B?
DBRX is the stronger model overall, scoring 29.0 to 27.9 on the Noometry Index.
Is DBRX or Gemma 3 4B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 32.3 in the Noometry coding category.
How many benchmarks do DBRX and Gemma 3 4B share?
13 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemma 3 4B has 22.