Model comparison
Codellama 34b Instruct vs DBRX
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and DBRX in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 24.3.
Side by side
| Codellama 34b Instruct | DBRX | |
|---|---|---|
| Provider | Meta | Databricks |
| Noometry Index | 30.8 | 29.4 |
| Released | — | 2024-03-27 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Codellama 34b Instruct: 28.5 (#314), DBRX: 32.9 (#266)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Coding | 1046 | 1132 |
| HumanEval+ | 43.9% | 70.1% |
| MBPP+ | 56.3% | 55.8% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
Reasoning DBRX leads
Codellama 34b Instruct: 19.6 (#255), DBRX: 21.4 (#222)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1113 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), DBRX: 24.3 (#269)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Math | 1056 | 1145 |
| MATH Level 5 | — | 11.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, DBRX: 14.9 (#294)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| GPQA Diamond | — | 32.9% |
| LMArena Expert | — | 1076 |
Multilingual DBRX leads
Codellama 34b Instruct: 25.8 (#284), DBRX: 29.3 (#268)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Non-English | 1011 | 1071 |
| LMArena Chinese | 976 | 1068 |
| LMArena French | — | 1096 |
| LMArena German | — | 1057 |
| LMArena Japanese | — | 990 |
| LMArena Korean | — | 993 |
| LMArena Russian | — | 1078 |
| LMArena Spanish | — | 1064 |
Instruction Following DBRX leads
Codellama 34b Instruct: 52.2 (#291), DBRX: 57.5 (#270)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Instruction Following | 1028 | 1112 |
Long Context DBRX leads
Codellama 34b Instruct: 30.9 (#284), DBRX: 33.7 (#258)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Longer Query | 1013 | 1112 |
Writing & Preference DBRX leads
Codellama 34b Instruct: 28.2 (#297), DBRX: 33.6 (#275)
| Benchmark | Codellama 34b Instruct | DBRX |
|---|---|---|
| LMArena Text | 1066 | 1119 |
| LMArena Creative Writing | 1032 | 1104 |
| LMArena Multi-Turn | 1015 | 1111 |
Frequently asked questions
Is Codellama 34b Instruct better than DBRX?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is Codellama 34b Instruct or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DBRX share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DBRX has 21.