Inkling 2 Small vs Kimi K3
Inkling 2 Small leads Kimi K3 by 0.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Inkling 2 Small wins 2 and Kimi K3 wins 3 of 5 shared benchmarks. Inkling 2 Small is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Inkling 2 Small | Kimi K3 |
|---|---|---|
| Agentic coding | 62 | 63 |
| Long-horizon autonomy | 66 | 65 |
| Knowledge-work agents | 42 | 42 |
| Computer use | 44 | 43 |
| Security & context learning | 54 | 53 |
Shared benchmarks
| Benchmark | Inkling 2 Small | Kimi K3 |
|---|---|---|
| APEX-Agentsindex | 46.8% | 47.8% |
| FrontierSWEindex | 25.1% | 25.9% |
| ARC-AGI | 96.5% | 94.5% |
| ARC-AGI-2 | 81.7% | 60.4% |
| SciCode | 52.3% | 59.5% |
Specs and price
| Inkling 2 Small | Kimi K3 | |
|---|---|---|
| Agent Index | 55.2 (#24) | 54.9 (#26) |
| Agent $/M | $0.14 | $1.39 |
| Input / output $/M | $0.30 / $1.00 | $3.00 / $15.00 |
| Context | 1M | 1M |
| Released | Nov 5, 2026 | Jul 16, 2026 |
| Weights | Open | Open |
| API hosts | 6 | 29 |
Don’t pick one. Route.
Shogo can run Inkling 2 Small and Kimi K3 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo