Model comparison
DBRX vs Phi-3.5-mini
DBRX has enough public results to be ranked (#311); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Databricks
MicrosoftSide by side
| DBRX | Phi-3.5-mini | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 29.4 | 36.9 |
| Released | 2024-03-27 | 2024-08-16 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-3.5-mini leads
DBRX: 32.9 (#266), Phi-3.5-mini: 34.6 (#232)
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1132 | — |
| BigCodeBench Complete | — | 38.5% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Not comparable
DBRX: 21.4 (#222), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| LMArena Hard Prompts | 1113 | — |
| PIQA | — | 81% |
Math Not comparable
DBRX: 24.3 (#269), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| LMArena Math | 1145 | — |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
DBRX: 14.9 (#294), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
| BoolQ | — | 78% |
Multilingual Not comparable
DBRX: 29.3 (#268), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| 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 Not comparable
DBRX: 57.5 (#270), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1112 | — |
Long Context Not comparable
DBRX: 33.7 (#258), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference Not comparable
DBRX: 33.6 (#275), Phi-3.5-mini: —
| Benchmark | DBRX | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1119 | — |
| LMArena Creative Writing | 1104 | — |
| LMArena Multi-Turn | 1111 | — |
Frequently asked questions
Is DBRX better than Phi-3.5-mini?
DBRX has enough public results to be ranked (#311); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is DBRX or Phi-3.5-mini better for coding?
Phi-3.5-mini scores higher on coding benchmarks: 34.6 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Phi-3.5-mini share?
0 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi-3.5-mini has 5.