Model comparison
DBRX vs Phi 3 Mini 4k Instruct
DBRX is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Databricks
MicrosoftSummary
- They share 19 benchmarks with published results for both. DBRX scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Mini 4k Instruct leads 28.5 to 14.9.
Side by side
| DBRX | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 29.4 | 27.9 |
| Released | 2024-03-27 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1132 | 1093 |
| HumanEval+ | 70.1% | 59.1% |
| MBPP+ | 55.8% | 54.2% |
| LiveBench Coding | — | 15.5% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
DBRX: 24.3 (#269), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1145 | 1111 |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 11.7% | — |
Knowledge Phi 3 Mini 4k Instruct leads
DBRX: 14.9 (#294), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1076 | 1045 |
| GPQA Diamond | 32.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1071 | 1021 |
| LMArena Chinese | 1068 | 1021 |
| LMArena French | 1096 | 1076 |
| LMArena German | 1057 | 1044 |
| LMArena Japanese | 990 | 935 |
| LMArena Korean | 993 | 905 |
| LMArena Russian | 1078 | 1022 |
| LMArena Spanish | 1064 | 1085 |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context DBRX leads
DBRX: 33.7 (#258), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | 1044 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | DBRX | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1119 | 1073 |
| LMArena Creative Writing | 1104 | 1037 |
| LMArena Multi-Turn | 1111 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is DBRX better than Phi 3 Mini 4k Instruct?
DBRX is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Is DBRX or Phi 3 Mini 4k Instruct better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 26.6 in the Noometry coding category.
How many benchmarks do DBRX and Phi 3 Mini 4k Instruct share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.