Model comparison
DBRX vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 29.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Databricks
StepFunSummary
- They share 15 benchmarks with published results for both. DBRX scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 14.9.
Side by side
| DBRX | Step 3 | |
|---|---|---|
| Provider | Databricks | StepFun |
| Noometry Index | 29.4 | 40.5 |
| 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 Step 3 leads
DBRX: 32.9 (#266), Step 3: 40.1 (#147)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Coding | 1132 | 1367 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Step 3 leads
DBRX: 21.4 (#222), Step 3: 28.4 (#105)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
DBRX: 24.3 (#269), Step 3: 37.6 (#148)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Math | 1145 | 1366 |
| MATH Level 5 | 11.7% | — |
Knowledge Step 3 leads
DBRX: 14.9 (#294), Step 3: 36.8 (#164)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Expert | 1076 | 1333 |
| GPQA Diamond | 32.9% | — |
Multimodal Not comparable
DBRX: —, Step 3: 35.5 (#86)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
DBRX: 29.3 (#268), Step 3: 46.3 (#159)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Non-English | 1071 | 1327 |
| LMArena Chinese | 1068 | 1397 |
| LMArena German | 1057 | 1371 |
| LMArena Korean | 993 | 1269 |
| LMArena Russian | 1078 | 1331 |
| LMArena Spanish | 1064 | 1371 |
| LMArena French | 1096 | — |
| LMArena Japanese | 990 | — |
Instruction Following Step 3 leads
DBRX: 57.5 (#270), Step 3: 70.4 (#164)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1332 |
Long Context Step 3 leads
DBRX: 33.7 (#258), Step 3: 40.3 (#157)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Longer Query | 1112 | 1326 |
Writing & Preference Step 3 leads
DBRX: 33.6 (#275), Step 3: 54.3 (#151)
| Benchmark | DBRX | Step 3 |
|---|---|---|
| LMArena Text | 1119 | 1350 |
| LMArena Creative Writing | 1104 | 1321 |
| LMArena Multi-Turn | 1111 | 1341 |
Frequently asked questions
Is DBRX better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 29.4 on the Noometry Index.
Is DBRX or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Step 3 share?
15 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Step 3 has 17.