Model comparison
Granite 4.2 3b vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 39.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 0 categories and Kimi K3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 26.0.
Side by side
| Granite 4.2 3b | Kimi K3 | |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 39.4 | 59.5 |
| Released | — | 2026-07-16 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 11 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Granite 4.2 3b: 40.0 (#151), Kimi K3: 61.0 (#10)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Coding | 1361 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| ALE-Bench | — | 1,524 |
Agentic & Tool Use Not comparable
Granite 4.2 3b: —, Kimi K3: 41.8 (#20)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Granite 4.2 3b: 26.0 (#138), Kimi K3: 63.0 (#17)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
Math Not comparable
Granite 4.2 3b: —, Kimi K3: 74.2 (#16)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |
| LMArena Math | — | 1491 |
Knowledge Kimi K3 leads
Granite 4.2 3b: 36.3 (#171), Kimi K3: 63.2 (#21)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Expert | 1315 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
Multimodal Not comparable
Granite 4.2 3b: —, Kimi K3: 37.8 (#70)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Granite 4.2 3b: 42.1 (#198), Kimi K3: 56.3 (#21)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1268 | 1466 |
| LMArena Chinese | 1269 | 1529 |
| LMArena Russian | 1249 | 1482 |
| LMArena French | — | 1491 |
| LMArena German | — | 1488 |
| LMArena Japanese | — | 1487 |
| LMArena Korean | — | 1458 |
| LMArena Spanish | — | 1472 |
Instruction Following Kimi K3 leads
Granite 4.2 3b: 67.1 (#200), Kimi K3: 77.7 (#14)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1273 | 1483 |
Long Context Kimi K3 leads
Granite 4.2 3b: 39.2 (#185), Kimi K3: 45.8 (#29)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1291 | 1494 |
Writing & Preference Kimi K3 leads
Granite 4.2 3b: 47.2 (#212), Kimi K3: 76.6 (#4)
| Benchmark | Granite 4.2 3b | Kimi K3 |
|---|---|---|
| LMArena Text | 1293 | 1476 |
| LMArena Creative Writing | 1205 | 1454 |
| LMArena Multi-Turn | 1290 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Granite 4.2 3b better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 39.4 on the Noometry Index.
Is Granite 4.2 3b or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 40.0 in the Noometry coding category.
How many benchmarks do Granite 4.2 3b and Kimi K3 share?
11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Kimi K3 has 53.