Model comparison
Granite 4.1 30B vs Kimi K2.6
Kimi K2.6 has enough public results to be ranked (#52); Granite 4.1 30B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. Granite 4.1 30B scores higher in 0 categories and Kimi K2.6 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 39.6 to 21.7.
- The biggest single-benchmark swing is SciCode: 25.8% for Granite 4.1 30B and 53.5% for Kimi K2.6.
Side by side
| Granite 4.1 30B | Kimi K2.6 | |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 33.4 | 47.5 |
| Released | 2026-04-29 | 2026-04-20 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 2 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Granite 4.1 30B: 34.6, Kimi K2.6: 50.5 (#41)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| SciCode | 25.8% | 53.5% |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1509 |
| WeirdML | — | 55.9% |
| LMArena Coding | — | 1488 |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
Granite 4.1 30B: —, Kimi K2.6: 21.8 (#128)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Granite 4.1 30B: 21.7, Kimi K2.6: 39.6 (#51)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| CritPt | 0% | 8% |
| NYT Connections (extended) | — | 87.2% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| LMArena Hard Prompts | — | 1470 |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.03 |
Math Not comparable
Granite 4.1 30B: —, Kimi K2.6: 56.8 (#34)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| LMArena Math | — | 1475 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Granite 4.1 30B: —, Kimi K2.6: 53.9 (#48)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
| LMArena Expert | — | 1491 |
Multimodal Not comparable
Granite 4.1 30B: —, Kimi K2.6: 31.8 (#95)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Not comparable
Granite 4.1 30B: —, Kimi K2.6: 55.1 (#35)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | — | 1446 |
| LMArena Chinese | — | 1521 |
| LMArena French | — | 1471 |
| LMArena German | — | 1449 |
| LMArena Japanese | — | 1442 |
| LMArena Korean | — | 1428 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1463 |
Instruction Following Not comparable
Granite 4.1 30B: —, Kimi K2.6: 76.5 (#40)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | — | 1451 |
Long Context Not comparable
Granite 4.1 30B: —, Kimi K2.6: 44.9 (#50)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | — | 1468 |
Writing & Preference Not comparable
Granite 4.1 30B: —, Kimi K2.6: 68.7 (#25)
| Benchmark | Granite 4.1 30B | Kimi K2.6 |
|---|---|---|
| LMArena Text | — | 1455 |
| LMArena Creative Writing | — | 1434 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
| LMArena Multi-Turn | — | 1453 |
Frequently asked questions
Is Granite 4.1 30B better than Kimi K2.6?
Kimi K2.6 has enough public results to be ranked (#52); Granite 4.1 30B does not yet, so treat this comparison as directional.
Is Granite 4.1 30B or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 34.6 in the Noometry coding category.
How many benchmarks do Granite 4.1 30B and Kimi K2.6 share?
2 benchmarks have published results for both models. Granite 4.1 30B has 2 scored results on Noometry and Kimi K2.6 has 51.