Model comparison
Granite 4.2 30b vs Kimi K2 (Jul 2025)
Granite 4.2 30b and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 4 categories and Kimi K2 (Jul 2025) in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 53.8.
Side by side
| Granite 4.2 30b | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 41.8 | 41.2 |
| Released | — | 2025-07-12 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.57 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 11 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Granite 4.2 30b: 41.0 (#126), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1396 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
Granite 4.2 30b: —, Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning Granite 4.2 30b leads
Granite 4.2 30b: 27.8 (#112), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1384 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |
Math Not comparable
Granite 4.2 30b: —, Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1397 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Granite 4.2 30b leads
Granite 4.2 30b: 39.1 (#138), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1406 | 1365 |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multilingual Kimi K2 (Jul 2025) leads
Granite 4.2 30b: 47.3 (#151), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1340 | 1372 |
| LMArena Chinese | 1414 | 1415 |
| LMArena Russian | 1343 | 1385 |
| LMArena French | — | 1379 |
| LMArena German | — | 1387 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1325 |
| LMArena Spanish | — | 1386 |
Instruction Following Too close to call
Granite 4.2 30b: 71.2 (#155), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1347 | 1348 |
| IFEval | — | 85% |
Long Context Too close to call
Granite 4.2 30b: 41.4 (#140), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1359 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Granite 4.2 30b: 53.8 (#156), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Granite 4.2 30b | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1361 | 1380 |
| LMArena Creative Writing | 1288 | 1350 |
| LMArena Multi-Turn | 1339 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
Frequently asked questions
Is Granite 4.2 30b better than Kimi K2 (Jul 2025)?
Granite 4.2 30b and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Is Granite 4.2 30b or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 41.0 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Kimi K2 (Jul 2025) share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Kimi K2 (Jul 2025) has 42.