Model comparison
Claude 2 vs DBRX
DBRX is the stronger model overall, scoring 29.4 to 25.0 on the Noometry Index.
Last verified . 3 shared benchmarks.
DatabricksSummary
- They share 3 benchmarks with published results for both. Claude 2 scores higher in 2 categories and DBRX in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 9.3.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | DBRX | |
|---|---|---|
| Provider | Anthropic | Databricks |
| Noometry Index | 25.0 | 29.4 |
| Released | 2023-07-11 | 2024-03-27 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, DBRX: 32.9 (#266)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| HumanEval+ | 61.6% | 70.1% |
| LMArena Coding | — | 1132 |
| MBPP+ | — | 55.8% |
Reasoning Too close to call
Claude 2: 21.7 (#216), DBRX: 21.4 (#222)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| LMArena Hard Prompts | — | 1113 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.13 | — |
Math DBRX leads
Claude 2: 9.3 (#320), DBRX: 24.3 (#269)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| MATH Level 5 | 11.7% | 11.7% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1145 |
Knowledge Claude 2 leads
Claude 2: 16.9 (#287), DBRX: 14.9 (#294)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| GPQA Diamond | 34.7% | 32.9% |
| LMArena Expert | — | 1076 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, DBRX: 29.3 (#268)
| Benchmark | Claude 2 | 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: —, DBRX: 57.5 (#270)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| LMArena Instruction Following | — | 1112 |
Long Context Not comparable
Claude 2: —, DBRX: 33.7 (#258)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| LMArena Longer Query | — | 1112 |
Writing & Preference Not comparable
Claude 2: —, DBRX: 33.6 (#275)
| Benchmark | Claude 2 | DBRX |
|---|---|---|
| LMArena Text | — | 1119 |
| LMArena Creative Writing | — | 1104 |
| LMArena Multi-Turn | — | 1111 |
Frequently asked questions
Is Claude 2 better than DBRX?
DBRX is the stronger model overall, scoring 29.4 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and DBRX share?
3 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and DBRX has 21.