Model comparison
Claude 2.1 vs DBRX
DBRX is the stronger model overall, scoring 29.4 to 25.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
DatabricksSummary
- They share 1 benchmark with published results for both. Claude 2.1 scores higher in 2 categories and DBRX in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 10.2.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | DBRX | |
|---|---|---|
| Provider | Anthropic | Databricks |
| Noometry Index | 25.2 | 29.4 |
| Released | 2023-11-21 | 2024-03-27 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Claude 2.1: 26.2 (#327), DBRX: 32.9 (#266)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1132 |
| HumanEval+ | — | 70.1% |
| MBPP+ | — | 55.8% |
Reasoning Too close to call
Claude 2.1: 21.4 (#221), DBRX: 21.4 (#222)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| LMArena Hard Prompts | — | 1113 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |
Math DBRX leads
Claude 2.1: 10.2 (#315), DBRX: 24.3 (#269)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1145 |
| MATH Level 5 | — | 11.7% |
Knowledge Too close to call
Claude 2.1: 15.4 (#292), DBRX: 14.9 (#294)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| GPQA Diamond | 33% | 32.9% |
| LMArena Expert | — | 1076 |
| MMLU | 73.5% | — |
Multilingual Not comparable
Claude 2.1: —, DBRX: 29.3 (#268)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| LMArena Non-English | — | 1071 |
| LMArena Chinese | — | 1068 |
| LMArena French | — | 1096 |
| LMArena German | — | 1057 |
| LMArena Japanese | — | 990 |
| LMArena Korean | — | 993 |
| LMArena Russian | — | 1078 |
| LMArena Spanish | — | 1064 |
Instruction Following Not comparable
Claude 2.1: —, DBRX: 57.5 (#270)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| LMArena Instruction Following | — | 1112 |
Long Context Not comparable
Claude 2.1: —, DBRX: 33.7 (#258)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| LMArena Longer Query | — | 1112 |
Writing & Preference Not comparable
Claude 2.1: —, DBRX: 33.6 (#275)
| Benchmark | Claude 2.1 | DBRX |
|---|---|---|
| LMArena Text | — | 1119 |
| LMArena Creative Writing | — | 1104 |
| LMArena Multi-Turn | — | 1111 |
Frequently asked questions
Is Claude 2.1 better than DBRX?
DBRX is the stronger model overall, scoring 29.4 to 25.2 on the Noometry Index.
Is Claude 2.1 or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and DBRX share?
1 benchmark has published results for both models. Claude 2.1 has 7 scored results on Noometry and DBRX has 21.