Inkling Small — Benchmarks
Benchmark scores for Inkling Small aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #72 of 123 open modelscomposite 43.7/100 across 7 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 48.7% | #10 / 50 | #67 / 155 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 19.1% | #14 / 15 | #66 / 78 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 90.0% | #12 / 74 | #58 / 270 |
| ProofBench | 6.0% | #15 / 21 | #55 / 64 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 88.5% | #11 / 83 | #47 / 291 |
| ARC-AGI | 84.0% | #4 / 16 | #68 / 200 |
| CritPt | 8.3% | #9 / 50 | #70 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.