Model comparison
DBRX vs Phi-2
DBRX has enough public results to be ranked (#307); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Databricks
MicrosoftSummary
- They share 2 benchmarks with published results for both.
Side by side
| DBRX | Phi-2 | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 29.0 | — |
| Released | 2024-03-27 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DBRX: 32.3 (#262), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| HumanEval+ | 70.1% | 45.1% |
| MBPP+ | 55.8% | 54.2% |
| LMArena Coding | 1132 | — |
Reasoning Not comparable
DBRX: 20.5 (#218), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1113 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
DBRX: 22.3 (#265), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Math | 1145 | — |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#289), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
DBRX: 29.4 (#263), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Non-English | 1071 | — |
| LMArena Chinese | 1068 | — |
| LMArena French | 1095 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Not comparable
DBRX: 57.7 (#265), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1112 | — |
Long Context Not comparable
DBRX: 33.7 (#253), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference Not comparable
DBRX: 33.7 (#271), Phi-2: —
| Benchmark | DBRX | Phi-2 |
|---|---|---|
| LMArena Text | 1119 | — |
| LMArena Creative Writing | 1104 | — |
| LMArena Multi-Turn | 1111 | — |
Frequently asked questions
Is DBRX better than Phi-2?
DBRX has enough public results to be ranked (#307); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do DBRX and Phi-2 share?
2 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi-2 has 11.