Model comparison
DBRX vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Databricks
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. DBRX scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| DBRX | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Databricks | Allen Institute for AI (Ai2) |
| Noometry Index | 29.4 | 33.0 |
| Released | 2024-03-27 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
DBRX: 32.9 (#266), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1132 | 1235 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
DBRX: 21.4 (#222), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1220 |
Math DBRX leads
DBRX: 24.3 (#269), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1145 | 1242 |
| MATH Level 5 | 11.7% | 42.7% |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
Knowledge Tulu 3 (Tülu 3) 70B leads
DBRX: 14.9 (#294), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 32.9% | 46.3% |
| LMArena Expert | 1076 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
DBRX: 29.3 (#268), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1071 | 1236 |
| LMArena Chinese | 1068 | 1249 |
| LMArena Russian | 1078 | 1246 |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
DBRX: 57.5 (#270), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
DBRX: 33.7 (#258), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1112 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
DBRX: 33.6 (#275), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | DBRX | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1119 | 1256 |
| LMArena Creative Writing | 1104 | 1231 |
| LMArena Multi-Turn | 1111 | 1252 |
Frequently asked questions
Is DBRX better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.4 on the Noometry Index.
Is DBRX or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.