Model comparison
Claude 3 Sonnet vs DBRX
Claude 3 Sonnet and DBRX score almost the same on the Noometry Index (29.0 vs 29.4), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
DatabricksSummary
- They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and DBRX in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 10.7.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 32.9% for DBRX.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | DBRX | |
|---|---|---|
| Provider | Anthropic | Databricks |
| Noometry Index | 29.0 | 29.4 |
| Released | 2024-02-29 | 2024-03-27 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Claude 3 Sonnet: 29.6 (#302), DBRX: 32.9 (#266)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Coding | 1223 | 1132 |
| HumanEval+ | 64% | 70.1% |
| MBPP+ | 69.3% | 55.8% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
Reasoning Too close to call
Claude 3 Sonnet: 20.5 (#237), DBRX: 21.4 (#222)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1113 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math DBRX leads
Claude 3 Sonnet: 10.7 (#310), DBRX: 24.3 (#269)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Math | 1213 | 1145 |
| MATH Level 5 | 18.2% | 11.7% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#276), DBRX: 14.9 (#294)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| GPQA Diamond | 40.6% | 32.9% |
| LMArena Expert | 1173 | 1076 |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), DBRX: —
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), DBRX: 29.3 (#268)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Non-English | 1205 | 1071 |
| LMArena Chinese | 1189 | 1068 |
| LMArena French | 1229 | 1096 |
| LMArena German | 1204 | 1057 |
| LMArena Japanese | 1131 | 990 |
| LMArena Korean | 1128 | 993 |
| LMArena Russian | 1227 | 1078 |
| LMArena Spanish | 1204 | 1064 |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), DBRX: 57.5 (#270)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Instruction Following | 1199 | 1112 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#228), DBRX: 33.7 (#258)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Longer Query | 1211 | 1112 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), DBRX: 33.6 (#275)
| Benchmark | Claude 3 Sonnet | DBRX |
|---|---|---|
| LMArena Text | 1218 | 1119 |
| LMArena Creative Writing | 1186 | 1104 |
| LMArena Multi-Turn | 1227 | 1111 |
Frequently asked questions
Is Claude 3 Sonnet better than DBRX?
Claude 3 Sonnet and DBRX score almost the same on the Noometry Index (29.0 vs 29.4), so choose on price, context window or the category you care about most.
Is Claude 3 Sonnet or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and DBRX share?
21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DBRX has 21.