Model comparison
DBRX vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DatabricksSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 33.6.
Side by side
| DBRX | MiMo-V2.5 | |
|---|---|---|
| Provider | Databricks | Xiaomi |
| Noometry Index | 29.4 | 43.4 |
| Released | 2024-03-27 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
DBRX: 32.9 (#266), MiMo-V2.5: 43.9 (#81)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1132 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning MiMo-V2.5 leads
DBRX: 21.4 (#222), MiMo-V2.5: 28.6 (#101)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1450 |
| CritPt | — | 3.7% |
Math MiMo-V2.5 leads
DBRX: 24.3 (#269), MiMo-V2.5: 36.8 (#163)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1145 | 1436 |
| ProofBench | — | 16% |
| MATH Level 5 | 11.7% | — |
Knowledge MiMo-V2.5 leads
DBRX: 14.9 (#294), MiMo-V2.5: 40.8 (#115)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1076 | 1460 |
| GPQA Diamond | 32.9% | — |
Multimodal Not comparable
DBRX: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual MiMo-V2.5 leads
DBRX: 29.3 (#268), MiMo-V2.5: 51.9 (#99)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1071 | 1404 |
| LMArena Chinese | 1068 | 1468 |
| LMArena French | 1096 | 1447 |
| LMArena German | 1057 | 1421 |
| LMArena Japanese | 990 | 1306 |
| LMArena Korean | 993 | 1363 |
| LMArena Russian | 1078 | 1395 |
| LMArena Spanish | 1064 | 1416 |
Instruction Following MiMo-V2.5 leads
DBRX: 57.5 (#270), MiMo-V2.5: 75.5 (#60)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1434 |
Long Context MiMo-V2.5 leads
DBRX: 33.7 (#258), MiMo-V2.5: 44.2 (#73)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1112 | 1445 |
Writing & Preference MiMo-V2.5 leads
DBRX: 33.6 (#275), MiMo-V2.5: 61.6 (#86)
| Benchmark | DBRX | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1119 | 1428 |
| LMArena Creative Writing | 1104 | 1393 |
| LMArena Multi-Turn | 1111 | 1445 |
Frequently asked questions
Is DBRX better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.4 on the Noometry Index.
Is DBRX or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and MiMo-V2.5 share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and MiMo-V2.5 has 23.