Model comparison
DBRX vs Phi 3 Small 8k Instruct
DBRX and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.4 vs 29.3), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Databricks
MicrosoftSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Small 8k Instruct leads 29.1 to 14.9.
Side by side
| DBRX | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 29.4 | 29.3 |
| Released | 2024-03-27 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1132 | 1101 |
| LiveBench Coding | — | 20.3% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Phi 3 Small 8k Instruct leads
DBRX: 24.3 (#269), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1145 | 1151 |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 11.7% | — |
Knowledge Phi 3 Small 8k Instruct leads
DBRX: 14.9 (#294), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1076 | 1067 |
| GPQA Diamond | 32.9% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Too close to call
DBRX: 29.3 (#268), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1071 | 1058 |
| LMArena Chinese | 1068 | 1061 |
| LMArena French | 1096 | 1135 |
| LMArena German | 1057 | 1080 |
| LMArena Japanese | 990 | 966 |
| LMArena Korean | 993 | 894 |
| LMArena Russian | 1078 | 1111 |
| LMArena Spanish | 1064 | 1111 |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Too close to call
DBRX: 33.7 (#258), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | 1088 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | DBRX | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1119 | 1110 |
| LMArena Creative Writing | 1104 | 1083 |
| LMArena Multi-Turn | 1111 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is DBRX better than Phi 3 Small 8k Instruct?
DBRX and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.4 vs 29.3), so choose on price, context window or the category you care about most.
Is DBRX or Phi 3 Small 8k Instruct better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 27.9 in the Noometry coding category.
How many benchmarks do DBRX and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi 3 Small 8k Instruct has 32.