Model comparison
DBRX vs Yi-34B
DBRX is the stronger model overall, scoring 29.4 to 27.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
DatabricksSummary
- They share 19 benchmarks with published results for both. DBRX scores higher in 6 categories and Yi-34B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DBRX leads 14.9 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 14.7% for Yi-34B.
Side by side
| DBRX | Yi-34B | |
|---|---|---|
| Provider | Databricks | 01.AI |
| Noometry Index | 29.4 | 27.8 |
| Released | 2024-03-27 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Yi-34B: 32.3 (#274)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Coding | 1132 | 1112 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Too close to call
DBRX: 21.4 (#222), Yi-34B: 21.2 (#226)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math DBRX leads
DBRX: 24.3 (#269), Yi-34B: 21.6 (#282)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Math | 1145 | 1114 |
| MATH Level 5 | 11.7% | 5.1% |
| GSM8K | — | 76% |
Knowledge DBRX leads
DBRX: 14.9 (#294), Yi-34B: 7.5 (#309)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| GPQA Diamond | 32.9% | 14.7% |
| LMArena Expert | 1076 | 1061 |
| MMLU | — | 76.3% |
Multilingual Too close to call
DBRX: 29.3 (#268), Yi-34B: 29.7 (#264)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Non-English | 1071 | 1079 |
| LMArena Chinese | 1068 | 1176 |
| LMArena French | 1096 | 1081 |
| LMArena German | 1057 | 1042 |
| LMArena Japanese | 990 | 993 |
| LMArena Korean | 993 | 959 |
| LMArena Russian | 1078 | 1050 |
| LMArena Spanish | 1064 | 1070 |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Yi-34B: 56.2 (#274)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1091 |
Long Context Too close to call
DBRX: 33.7 (#258), Yi-34B: 33.2 (#264)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1112 | 1094 |
Writing & Preference Too close to call
DBRX: 33.6 (#275), Yi-34B: 34.1 (#273)
| Benchmark | DBRX | Yi-34B |
|---|---|---|
| LMArena Text | 1119 | 1129 |
| LMArena Creative Writing | 1104 | 1108 |
| LMArena Multi-Turn | 1111 | 1113 |
Frequently asked questions
Is DBRX better than Yi-34B?
DBRX is the stronger model overall, scoring 29.4 to 27.8 on the Noometry Index.
Is DBRX or Yi-34B better for coding?
They score almost the same on coding (32.9 vs 32.3); test both on your own repository before choosing.
How many benchmarks do DBRX and Yi-34B share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Yi-34B has 23.