Model comparison
DBRX vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
MicrosoftSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 1 category and Phi 3 Medium 4k Instruct in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Medium 4k Instruct leads 29.6 to 14.9.
Side by side
| DBRX | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 29.0 | 32.4 |
| Released | 2024-03-27 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.3 (#262), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1132 | 1130 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Too close to call
DBRX: 20.5 (#218), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1127 |
Math Phi 3 Medium 4k Instruct leads
DBRX: 22.3 (#265), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1145 | 1173 |
| MATH Level 5 | 11.7% | — |
Knowledge Phi 3 Medium 4k Instruct leads
DBRX: 14.9 (#289), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1076 | 1108 |
| GPQA Diamond | 32.9% | — |
Multilingual Phi 3 Medium 4k Instruct leads
DBRX: 29.4 (#263), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1071 | 1094 |
| LMArena Chinese | 1068 | 1108 |
| LMArena French | 1095 | 1109 |
| LMArena German | 1057 | 1101 |
| LMArena Japanese | 990 | 1042 |
| LMArena Korean | 993 | 954 |
| LMArena Russian | 1078 | 1145 |
| LMArena Spanish | 1064 | 1095 |
Instruction Following Too close to call
DBRX: 57.7 (#265), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | 1114 |
Long Context Too close to call
DBRX: 33.7 (#253), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | 1120 |
Writing & Preference Too close to call
DBRX: 33.7 (#271), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | DBRX | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1119 | 1138 |
| LMArena Creative Writing | 1104 | 1106 |
| LMArena Multi-Turn | 1111 | 1088 |
Frequently asked questions
Is DBRX better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.0 on the Noometry Index.
Is DBRX or Phi 3 Medium 4k Instruct better for coding?
They score almost the same on coding (32.3 vs 32.3); test both on your own repository before choosing.
How many benchmarks do DBRX and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.