Model comparison
Granite 4.2 30b vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 41.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 1 category and Kimi K2 Thinking Turbo in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 38.5.
Side by side
| Granite 4.2 30b | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 41.4 | 45.4 |
| Released | — | 2025-11-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
Granite 4.2 30b: 40.4 (#127), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1394 | 1454 |
| LMArena WebDev | — | 1322 |
Reasoning Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 26.7 (#114), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1428 |
| Chess Puzzles | — | 20% |
Math Not comparable
Granite 4.2 30b: —, Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 83.1% |
| LMArena Math | — | 1429 |
Knowledge Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 38.5 (#134), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Expert | 1405 | 1439 |
| GPQA Diamond | — | 84.2% |
Multilingual Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 47.4 (#146), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1340 | 1398 |
| LMArena Chinese | 1415 | 1457 |
| LMArena Russian | 1342 | 1390 |
| LMArena French | — | 1425 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1356 |
| LMArena Korean | — | 1329 |
| LMArena Spanish | — | 1407 |
Instruction Following Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 71.3 (#150), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1346 | 1403 |
Long Context Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 41.4 (#135), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1359 | 1415 |
Writing & Preference Kimi K2 Thinking Turbo leads
Granite 4.2 30b: 54.3 (#147), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | Granite 4.2 30b | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1363 | 1415 |
| LMArena Creative Writing | 1294 | 1373 |
| LMArena Multi-Turn | 1340 | 1414 |
Frequently asked questions
Is Granite 4.2 30b better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 41.4 on the Noometry Index.
Is Granite 4.2 30b or Kimi K2 Thinking Turbo better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 38.1 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Kimi K2 Thinking Turbo share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Kimi K2 Thinking Turbo has 21.