Model comparison
DBRX vs Llama 3.1 Tulu 3 8b
Llama 3.1 Tulu 3 8b is the stronger model overall, scoring 35.7 to 29.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Databricks
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. DBRX scores higher in 0 categories and Llama 3.1 Tulu 3 8b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.1 Tulu 3 8b leads 33.9 to 24.3.
Side by side
| DBRX | Llama 3.1 Tulu 3 8b | |
|---|---|---|
| Provider | Databricks | Allen Institute for AI (Ai2) |
| Noometry Index | 29.4 | 35.7 |
| Released | 2024-03-27 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Tulu 3 8b leads
DBRX: 32.9 (#266), Llama 3.1 Tulu 3 8b: 34.4 (#235)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Coding | 1132 | 1183 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Llama 3.1 Tulu 3 8b leads
DBRX: 21.4 (#222), Llama 3.1 Tulu 3 8b: 22.8 (#188)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1174 |
Math Llama 3.1 Tulu 3 8b leads
DBRX: 24.3 (#269), Llama 3.1 Tulu 3 8b: 33.9 (#198)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Math | 1145 | 1195 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#294), Llama 3.1 Tulu 3 8b: —
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
Multilingual Llama 3.1 Tulu 3 8b leads
DBRX: 29.3 (#268), Llama 3.1 Tulu 3 8b: 35.4 (#246)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Non-English | 1071 | 1169 |
| LMArena Chinese | 1068 | 1176 |
| LMArena Russian | 1078 | 1193 |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Llama 3.1 Tulu 3 8b leads
DBRX: 57.5 (#270), Llama 3.1 Tulu 3 8b: 61.3 (#246)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Instruction Following | 1112 | 1174 |
Long Context Llama 3.1 Tulu 3 8b leads
DBRX: 33.7 (#258), Llama 3.1 Tulu 3 8b: 35.8 (#239)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Longer Query | 1112 | 1181 |
Writing & Preference Llama 3.1 Tulu 3 8b leads
DBRX: 33.6 (#275), Llama 3.1 Tulu 3 8b: 39.7 (#245)
| Benchmark | DBRX | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Text | 1119 | 1193 |
| LMArena Creative Writing | 1104 | 1182 |
| LMArena Multi-Turn | 1111 | 1154 |
Frequently asked questions
Is DBRX better than Llama 3.1 Tulu 3 8b?
Llama 3.1 Tulu 3 8b is the stronger model overall, scoring 35.7 to 29.4 on the Noometry Index.
Is DBRX or Llama 3.1 Tulu 3 8b better for coding?
Llama 3.1 Tulu 3 8b scores higher on coding benchmarks: 34.4 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Llama 3.1 Tulu 3 8b share?
11 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3.1 Tulu 3 8b has 11.