Model comparison
DBRX vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Databricks
GoogleSummary
- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Gemini 3.1 Pro Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.1 Pro Preview leads 71.8 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 94.4% for Gemini 3.1 Pro Preview.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 29.4 | 56.7 |
| Released | 2024-03-27 | 2026-02-19 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 21 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
DBRX: 32.9 (#266), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Coding | 1132 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| MirrorCode | — | 8.9% |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
DBRX: 21.4 (#222), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1485 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.1% |
| LMCA | — | 53.8% |
| Epoch Capabilities Index | — | 154.77 |
| ForecastBench | — | 59 |
Math Gemini 3.1 Pro Preview leads
DBRX: 24.3 (#269), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Math | 1145 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| MATH Level 5 | 11.7% | — |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
DBRX: 14.9 (#294), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 32.9% | 94.4% |
| LMArena Expert | 1076 | 1485 |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
Multimodal Not comparable
DBRX: —, Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
DBRX: 29.3 (#268), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1071 | 1477 |
| LMArena Chinese | 1068 | 1529 |
| LMArena French | 1096 | 1487 |
| LMArena German | 1057 | 1491 |
| LMArena Japanese | 990 | 1493 |
| LMArena Korean | 993 | 1455 |
| LMArena Russian | 1078 | 1498 |
| LMArena Spanish | 1064 | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
DBRX: 57.5 (#270), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1112 | 1466 |
Long Context Gemini 3.1 Pro Preview leads
DBRX: 33.7 (#258), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1112 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
DBRX: 33.6 (#275), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | DBRX | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1119 | 1481 |
| LMArena Creative Writing | 1104 | 1482 |
| LMArena Multi-Turn | 1111 | 1488 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
Frequently asked questions
Is DBRX better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.4 on the Noometry Index.
Is DBRX or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Gemini 3.1 Pro Preview share?
18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemini 3.1 Pro Preview has 71.