Model comparison
Claude 3 Haiku vs DBRX
DBRX is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
DatabricksSummary
- They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and DBRX in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 9.8.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | DBRX | |
|---|---|---|
| Provider | Anthropic | Databricks |
| Noometry Index | 25.9 | 29.4 |
| Released | 2024-03-07 | 2024-03-27 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Claude 3 Haiku: 26.4 (#325), DBRX: 32.9 (#266)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Coding | 1199 | 1132 |
| HumanEval+ | 68.9% | 70.1% |
| MBPP+ | 68.8% | 55.8% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
Reasoning DBRX leads
Claude 3 Haiku: 16.3 (#307), DBRX: 21.4 (#222)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1113 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math DBRX leads
Claude 3 Haiku: 9.8 (#319), DBRX: 24.3 (#269)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Math | 1188 | 1145 |
| MATH Level 5 | 14.9% | 11.7% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#285), DBRX: 14.9 (#294)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| GPQA Diamond | 36.3% | 32.9% |
| LMArena Expert | 1148 | 1076 |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), DBRX: —
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), DBRX: 29.3 (#268)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Non-English | 1178 | 1071 |
| LMArena Chinese | 1155 | 1068 |
| LMArena French | 1195 | 1096 |
| LMArena German | 1174 | 1057 |
| LMArena Japanese | 1102 | 990 |
| LMArena Korean | 1109 | 993 |
| LMArena Russian | 1204 | 1078 |
| LMArena Spanish | 1166 | 1064 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), DBRX: 57.5 (#270)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Instruction Following | 1173 | 1112 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), DBRX: 33.7 (#258)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Longer Query | 1190 | 1112 |
Writing & Preference DBRX leads
Claude 3 Haiku: 29.7 (#291), DBRX: 33.6 (#275)
| Benchmark | Claude 3 Haiku | DBRX |
|---|---|---|
| LMArena Text | 1195 | 1119 |
| LMArena Creative Writing | 1157 | 1104 |
| LMArena Multi-Turn | 1190 | 1111 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than DBRX?
DBRX is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and DBRX share?
21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and DBRX has 21.