Model comparison
DBRX vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
Mistral AISummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 14.9.
Side by side
| DBRX | Magistral Medium | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 29.4 | 35.2 |
| Released | 2024-03-27 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
DBRX: 32.9 (#266), Magistral Medium: 39.1 (#161)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Coding | 1132 | 1319 |
| SciCode | — | 39.2% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Magistral Medium: 8.6 (#348)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
Math Magistral Medium leads
DBRX: 24.3 (#269), Magistral Medium: 35.1 (#189)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Math | 1145 | 1250 |
| MATH Level 5 | 11.7% | — |
Knowledge Magistral Medium leads
DBRX: 14.9 (#294), Magistral Medium: 33.5 (#202)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Expert | 1076 | 1223 |
| GPQA Diamond | 32.9% | — |
Multilingual Magistral Medium leads
DBRX: 29.3 (#268), Magistral Medium: 39.6 (#224)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1071 | 1232 |
| LMArena Chinese | 1068 | 1227 |
| LMArena French | 1096 | 1267 |
| LMArena German | 1057 | 1248 |
| LMArena Japanese | 990 | 1175 |
| LMArena Korean | 993 | 1125 |
| LMArena Russian | 1078 | 1224 |
| LMArena Spanish | 1064 | 1271 |
Instruction Following Magistral Medium leads
DBRX: 57.5 (#270), Magistral Medium: 66.0 (#211)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1112 | 1254 |
Long Context Magistral Medium leads
DBRX: 33.7 (#258), Magistral Medium: 39.3 (#183)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1112 | 1295 |
Writing & Preference Magistral Medium leads
DBRX: 33.6 (#275), Magistral Medium: 46.3 (#219)
| Benchmark | DBRX | Magistral Medium |
|---|---|---|
| LMArena Text | 1119 | 1255 |
| LMArena Creative Writing | 1104 | 1245 |
| LMArena Multi-Turn | 1111 | 1275 |
Frequently asked questions
Is DBRX better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 29.4 on the Noometry Index.
Is DBRX or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Magistral Medium share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Magistral Medium has 22.