Model comparison
DBRX vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Databricks
MiniMaxSummary
- They share 15 benchmarks with published results for both. DBRX scores higher in 1 category and MiniMax-M2 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 14.9.
Side by side
| DBRX | MiniMax-M2 | |
|---|---|---|
| Provider | Databricks | MiniMax |
| Noometry Index | 29.4 | 37.4 |
| Released | 2024-03-27 | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
DBRX: 32.9 (#266), MiniMax-M2: 39.3 (#159)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1132 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, MiniMax-M2: 25.1 (#109)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning DBRX leads
DBRX: 21.4 (#222), MiniMax-M2: 19.4 (#258)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math MiniMax-M2 leads
DBRX: 24.3 (#269), MiniMax-M2: 37.3 (#160)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1145 | 1352 |
| MATH Level 5 | 11.7% | — |
Knowledge MiniMax-M2 leads
DBRX: 14.9 (#294), MiniMax-M2: 37.0 (#163)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1076 | 1337 |
| GPQA Diamond | 32.9% | — |
Multilingual MiniMax-M2 leads
DBRX: 29.3 (#268), MiniMax-M2: 45.3 (#171)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1071 | 1313 |
| LMArena Chinese | 1068 | 1366 |
| LMArena French | 1096 | 1335 |
| LMArena German | 1057 | 1355 |
| LMArena Russian | 1078 | 1331 |
| LMArena Spanish | 1064 | 1326 |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
Instruction Following MiniMax-M2 leads
DBRX: 57.5 (#270), MiniMax-M2: 70.2 (#166)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1328 |
Long Context MiniMax-M2 leads
DBRX: 33.7 (#258), MiniMax-M2: 40.5 (#153)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1112 | 1331 |
Writing & Preference MiniMax-M2 leads
DBRX: 33.6 (#275), MiniMax-M2: 53.0 (#162)
| Benchmark | DBRX | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1119 | 1340 |
| LMArena Creative Writing | 1104 | 1286 |
| LMArena Multi-Turn | 1111 | 1361 |
Frequently asked questions
Is DBRX better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.4 on the Noometry Index.
Is DBRX or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and MiniMax-M2 share?
15 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and MiniMax-M2 has 21.