Model comparison
DBRX vs Falcon-180B
Falcon-180B is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
Last verified . 6 shared benchmarks.
Databricks
Technology Innovation InstituteSummary
- They share 6 benchmarks with published results for both. DBRX scores higher in 4 categories and Falcon-180B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DBRX leads 33.6 to 29.1.
Side by side
| DBRX | Falcon-180B | |
|---|---|---|
| Provider | Databricks | Technology Innovation Institute |
| Noometry Index | 29.4 | 32.2 |
| Released | 2024-03-27 | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DBRX: 32.9 (#266), Falcon-180B: —
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Coding | 1132 | — |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Falcon-180B: 19.1 (#269)
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1007 |
| Epoch Capabilities Index | — | 112.13 |
| HellaSwag | — | 89% |
| LAMBADA | — | 79.8% |
| PIQA | — | 84.9% |
| WinoGrande | — | 87.1% |
Math Not comparable
DBRX: 24.3 (#269), Falcon-180B: —
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Math | 1145 | — |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 54.4% |
Knowledge Not comparable
DBRX: 14.9 (#294), Falcon-180B: —
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
| ARC (AI2) Challenge | — | 67.8% |
| BoolQ | — | 89% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 64.2% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Falcon-180B: 25.2 (#286)
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Non-English | 1071 | 1000 |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Falcon-180B: 53.4 (#286)
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1047 |
Long Context Not comparable
DBRX: 33.7 (#258), Falcon-180B: —
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Falcon-180B: 29.1 (#295)
| Benchmark | DBRX | Falcon-180B |
|---|---|---|
| LMArena Text | 1119 | 1054 |
| LMArena Creative Writing | 1104 | 1089 |
| LMArena Multi-Turn | 1111 | 1013 |
Frequently asked questions
Is DBRX better than Falcon-180B?
Falcon-180B is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
How many benchmarks do DBRX and Falcon-180B share?
6 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Falcon-180B has 16.