Grok 4.7 vs Inkling 2 Small
Inkling 2 Small leads Grok 4.7 by 0.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Grok 4.7 wins 3 and Inkling 2 Small wins 2 of 5 shared benchmarks. Inkling 2 Small is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Grok 4.7 | Inkling 2 Small |
|---|---|---|
| Agentic coding | 58 | 62 |
| Long-horizon autonomy | 69 | 66 |
| Knowledge-work agents | 47 | 42 |
| Computer use | 39 | 44 |
| Security & context learning | 50 | 54 |
Shared benchmarks
| Benchmark | Grok 4.7 | Inkling 2 Small |
|---|---|---|
| APEX-Agentsindex | 70.0% | 46.8% |
| FrontierSWEindex | 29.5% | 25.1% |
| ARC-AGI | 90.2% | 96.5% |
| ARC-AGI-2 | 61.4% | 81.7% |
| SciCode | 57.8% | 52.3% |
Specs and price
| Grok 4.7 | Inkling 2 Small | |
|---|---|---|
| Agent Index | 54.8 (#27) | 55.2 (#24) |
| Agent $/M | $0.98 | $0.14 |
| Input / output $/M | $2.00 / $6.00 | $0.30 / $1.00 |
| Context | 500K | 1M |
| Released | Sep 21, 2026 | Nov 5, 2026 |
| Weights | Closed | Open |
| API hosts | 5 | 6 |
Don’t pick one. Route.
Shogo can run Grok 4.7 and Inkling 2 Small side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo