Model comparison
DBRX vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Databricks
GoogleSummary
- They share 15 benchmarks with published results for both. DBRX scores higher in 0 categories and Gemma 4 31B IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 33.6.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 75.8% for Gemma 4 31B IT.
Side by side
| DBRX | Gemma 4 31B IT | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 29.4 | 43.5 |
| Released | 2024-03-27 | 2026-04-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.09 |
| Output $ / M tokens | — | $0.34 |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
DBRX: 32.9 (#266), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Coding | 1132 | 1459 |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 925.5 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Gemma 4 31B IT leads
DBRX: 21.4 (#222), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1448 |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| DTBench | — | 82.7% |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |
Math Gemma 4 31B IT leads
DBRX: 24.3 (#269), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Math | 1145 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| MATH Level 5 | 11.7% | — |
Knowledge Gemma 4 31B IT leads
DBRX: 14.9 (#294), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 32.9% | 75.8% |
| LMArena Expert | 1076 | 1465 |
| SimpleQA Verified | — | 10.4% |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
DBRX: —, Gemma 4 31B IT: 41.6 (#34)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1277 |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
DBRX: 29.3 (#268), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1071 | 1431 |
| LMArena Chinese | 1068 | 1476 |
| LMArena French | 1096 | 1435 |
| LMArena Russian | 1078 | 1460 |
| LMArena Spanish | 1064 | 1444 |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
Instruction Following Gemma 4 31B IT leads
DBRX: 57.5 (#270), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1112 | 1433 |
Long Context Gemma 4 31B IT leads
DBRX: 33.7 (#258), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1112 | 1446 |
Writing & Preference Gemma 4 31B IT leads
DBRX: 33.6 (#275), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | DBRX | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1119 | 1443 |
| LMArena Creative Writing | 1104 | 1415 |
| LMArena Multi-Turn | 1111 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is DBRX better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 29.4 on the Noometry Index.
Is DBRX or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Gemma 4 31B IT share?
15 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemma 4 31B IT has 35.