Up to four models
Inkling 2 Small vs Grok 4.7
On the index (GPT-4 = 100), Inkling 2 Small scores 166 and Grok 4.7 164. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
TMInkling 2 Small
166149–183
WeightsOpen
ReleasedNov 2026
Price in / out$0.30 / $1.0
Context1.05M
Core tests taken2 of 9
Grok 4.7
164149–180
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Inkling 2 Small and Grok 4.7 are too close to call (2 points apart, within the uncertainty), ahead on 0 of 2 shared core tests, and costs 6.3× less.
Test by testthird-party results
TMInkling 2 SmallGrok 4.7
Every result as a table
| Test | Inkling 2 Small | Grok 4.7 |
|---|---|---|
| Coding | ||
| Terminal-Bench 4.0 | 12.6% | 28.8% |
| CyberBench v1.1 | 72.7% | 69.5% |
| ProgramBench | 0.5% | 0.5% |
| Vibe Code Bench v1.1 | 81.5% | 86.2% |
| FrontierSWE | 25.1% | 29.5% |
| Agents | ||
| APEX-Agents | 46.8% | 70.0% |
| BioMysteryBench | 70.0% | 69.3% |
| SRE Bench | 1.9% | 3.8% |
| Terminal-Bench-Science | 2.9% | 10.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 21.7% | 18.3% |
| Legal Research Bench | 46.6% | 47.1% |
| SAGE | 88.6% | 88.7% |
| Tax Agent Bench | 38.9% | 35.8% |
| Novel problems | ||
| MysteryMechanism | 25.2% | 25.2% |
Tests at least two of these models have taken. Bold rows are the core tests.