Model comparison
DBRX vs Gemini 1.5 Flash (May 2024)
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 29.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Databricks
GoogleSummary
- They share 21 benchmarks with published results for both. DBRX scores higher in 1 category and Gemini 1.5 Flash (May 2024) in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Flash (May 2024) leads 48.7 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 61.9% for Gemini 1.5 Flash (May 2024).
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Gemini 1.5 Flash (May 2024) | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 29.4 | 33.2 |
| Released | 2024-03-27 | 2024-05-14 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Flash (May 2024) leads
DBRX: 32.9 (#266), Gemini 1.5 Flash (May 2024): 34.4 (#236)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Coding | 1132 | 1261 |
| HumanEval+ | 70.1% | 75.6% |
| MBPP+ | 55.8% | 67.5% |
| WeirdML | — | 24.9% |
| BigCodeBench Instruct | — | 43.5% |
| BigCodeBench Complete | — | 55.1% |
Agentic & Tool Use Not comparable
DBRX: —, Gemini 1.5 Flash (May 2024): 26.6 (#102)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| BALROG | — | 14.6% |
Reasoning Too close to call
DBRX: 21.4 (#222), Gemini 1.5 Flash (May 2024): 21.7 (#215)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1257 |
| DTBench | — | 53.8% |
| Epoch Capabilities Index | — | 129.36 |
| ForecastBench | — | 53.9 |
| PIQA | — | 87.5% |
Math DBRX leads
DBRX: 24.3 (#269), Gemini 1.5 Flash (May 2024): 22.1 (#281)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Math | 1145 | 1269 |
| MATH Level 5 | 11.7% | 61.9% |
| OTIS Mock AIME 2024-2025 | — | 16.3% |
| Omni-MATH | — | 30.4% |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | — | 82.4% |
Knowledge Gemini 1.5 Flash (May 2024) leads
DBRX: 14.9 (#294), Gemini 1.5 Flash (May 2024): 26.2 (#260)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| GPQA Diamond | 32.9% | 47.3% |
| LMArena Expert | 1076 | 1233 |
| MMLU-Pro | — | 67.8% |
| GPQA (HELM) | — | 43.7% |
| BoolQ | — | 85.8% |
| MMLU | — | 77.9% |
Multimodal Not comparable
DBRX: —, Gemini 1.5 Flash (May 2024): 36.0 (#81)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Vision | — | 1141 |
| Video-MME | — | 70.3% |
| GeoBench | — | 76% |
Multilingual Gemini 1.5 Flash (May 2024) leads
DBRX: 29.3 (#268), Gemini 1.5 Flash (May 2024): 42.9 (#189)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Non-English | 1071 | 1278 |
| LMArena Chinese | 1068 | 1295 |
| LMArena French | 1096 | 1258 |
| LMArena German | 1057 | 1262 |
| LMArena Japanese | 990 | 1252 |
| LMArena Korean | 993 | 1221 |
| LMArena Russian | 1078 | 1288 |
| LMArena Spanish | 1064 | 1243 |
Instruction Following Gemini 1.5 Flash (May 2024) leads
DBRX: 57.5 (#270), Gemini 1.5 Flash (May 2024): 66.8 (#205)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1112 | 1258 |
| IFEval | — | 83.1% |
Long Context Gemini 1.5 Flash (May 2024) leads
DBRX: 33.7 (#258), Gemini 1.5 Flash (May 2024): 39.0 (#187)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Longer Query | 1112 | 1284 |
Writing & Preference Gemini 1.5 Flash (May 2024) leads
DBRX: 33.6 (#275), Gemini 1.5 Flash (May 2024): 48.7 (#196)
| Benchmark | DBRX | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Text | 1119 | 1287 |
| LMArena Creative Writing | 1104 | 1285 |
| LMArena Multi-Turn | 1111 | 1253 |
| WildBench | — | 79.2% |
Frequently asked questions
Is DBRX better than Gemini 1.5 Flash (May 2024)?
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 29.4 on the Noometry Index.
Is DBRX or Gemini 1.5 Flash (May 2024) better for coding?
Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 34.4 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Gemini 1.5 Flash (May 2024) share?
21 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemini 1.5 Flash (May 2024) has 42.