Reasoning model with text and image input. Tracked independent measurements use xhigh effort; coverage remains partial. API specifications are reported by Artificial Analysis.
SI v3 uses weighted percentages from one Artificial Analysis configuration. Ranking requires all five benchmarks. Partial scores average only available weights. Scores are not comparable to SI v2 or a probability of reaching singularity.
Compared with 58 models released within six months of it, across 3 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 43.1% | #22 / 95 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisGrok 4.7 (Xhigh) | 43.1% |
Terminal-Bench 4.0 Artificial AnalysisGrok 4.7 (Xhigh) | 25.8% |
SciCode Artificial AnalysisGrok 4.7 (Xhigh) | 57.4% |
AA-LCR Artificial AnalysisGrok 4.7 (Xhigh) | 76.7% |
CritPt Artificial AnalysisGrok 4.7 (Xhigh) | 17.7% |
ITBench SRE Artificial AnalysisGrok 4.7 (Xhigh) | 42.1% |