Model comparison
Kimi K2.6 vs StarCoder 2 3B
Kimi K2.6 has enough public results to be ranked (#60); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. Kimi K2.6 scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Kimi K2.6 leads 50.7 to 33.5.
Side by side
| Kimi K2.6 | StarCoder 2 3B | |
|---|---|---|
| Provider | Moonshot AI | NVIDIA |
| Noometry Index | 47.7 | 36.3 |
| Released | 2026-04-20 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 51 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.7 (#43), StarCoder 2 3B: 33.5
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 53.5% | — |
| WeirdML | 55.9% | — |
| LMArena Coding | 1488 | — |
| BigCodeBench Complete | — | 21.4% |
| ALE-Bench | 1,093 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Kimi K2.6: 21.9 (#137), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |
Reasoning Not comparable
Kimi K2.6: 40.5 (#55), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 151.05 | 88.76 |
| NYT Connections (extended) | 87.2% | — |
| CritPt | 8% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| LMArena Hard Prompts | 1470 | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LMCA | 37.3% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Kimi K2.6: 57.0 (#41), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| 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% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Kimi K2.6: 54.0 (#54), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |
| LMArena Expert | 1491 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multimodal Not comparable
Kimi K2.6: 31.6 (#103), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Not comparable
Kimi K2.6: 54.9 (#37), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1446 | — |
| LMArena Chinese | 1521 | — |
| LMArena French | 1471 | — |
| LMArena German | 1450 | — |
| LMArena Japanese | 1443 | — |
| LMArena Korean | 1427 | — |
| LMArena Russian | 1446 | — |
| LMArena Spanish | 1464 | — |
Instruction Following Not comparable
Kimi K2.6: 76.3 (#43), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1451 | — |
Long Context Not comparable
Kimi K2.6: 44.9 (#52), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1468 | — |
Writing & Preference Not comparable
Kimi K2.6: 68.5 (#26), StarCoder 2 3B: —
| Benchmark | Kimi K2.6 | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1455 | — |
| LMArena Creative Writing | 1434 | — |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
| LMArena Multi-Turn | 1453 | — |
Frequently asked questions
Is Kimi K2.6 better than StarCoder 2 3B?
Kimi K2.6 has enough public results to be ranked (#60); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Kimi K2.6 or StarCoder 2 3B better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 33.5 in the Noometry coding category.
How many benchmarks do Kimi K2.6 and StarCoder 2 3B share?
1 benchmark has published results for both models. Kimi K2.6 has 51 scored results on Noometry and StarCoder 2 3B has 7.