Model comparison
DBRX vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
DatabricksSummary
- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 84.2% for Kimi K2 Thinking Turbo.
Side by side
| DBRX | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Databricks | Moonshot AI |
| Noometry Index | 29.4 | 45.8 |
| Released | 2024-03-27 | 2025-11-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
DBRX: 32.9 (#266), Kimi K2 Thinking Turbo: 38.4 (#178)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1132 | 1454 |
| LMArena WebDev | — | 1322 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Kimi K2 Thinking Turbo leads
DBRX: 21.4 (#222), Kimi K2 Thinking Turbo: 32.5 (#75)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1428 |
| Chess Puzzles | — | 20% |
Math Kimi K2 Thinking Turbo leads
DBRX: 24.3 (#269), Kimi K2 Thinking Turbo: 47.4 (#68)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Math | 1145 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 83.1% |
| MATH Level 5 | 11.7% | — |
Knowledge Kimi K2 Thinking Turbo leads
DBRX: 14.9 (#294), Kimi K2 Thinking Turbo: 50.9 (#69)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 32.9% | 84.2% |
| LMArena Expert | 1076 | 1439 |
Multilingual Kimi K2 Thinking Turbo leads
DBRX: 29.3 (#268), Kimi K2 Thinking Turbo: 51.4 (#109)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1071 | 1398 |
| LMArena Chinese | 1068 | 1456 |
| LMArena French | 1096 | 1425 |
| LMArena German | 1057 | 1390 |
| LMArena Japanese | 990 | 1357 |
| LMArena Korean | 993 | 1330 |
| LMArena Russian | 1078 | 1391 |
| LMArena Spanish | 1064 | 1406 |
Instruction Following Kimi K2 Thinking Turbo leads
DBRX: 57.5 (#270), Kimi K2 Thinking Turbo: 74.0 (#109)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1112 | 1403 |
Long Context Kimi K2 Thinking Turbo leads
DBRX: 33.7 (#258), Kimi K2 Thinking Turbo: 43.2 (#102)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1112 | 1415 |
Writing & Preference Kimi K2 Thinking Turbo leads
DBRX: 33.6 (#275), Kimi K2 Thinking Turbo: 60.0 (#104)
| Benchmark | DBRX | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1119 | 1415 |
| LMArena Creative Writing | 1104 | 1374 |
| LMArena Multi-Turn | 1111 | 1414 |
Frequently asked questions
Is DBRX better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.4 on the Noometry Index.
Is DBRX or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Kimi K2 Thinking Turbo share?
18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Kimi K2 Thinking Turbo has 21.