First model to score 100% on AIME 2025 and 80% on SWE-bench
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 41 models released within six months of it, across 8 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
MMLU Tests knowledge across 57 subjects from STEM to humanities | 93.8% | #1 / 54 |
MATH Competition-level mathematics problems | 100% | #1 / 50 |
ARC-C Grade-school science questions requiring reasoning | 98.9% | #1 / 40 |
HellaSwag Common sense reasoning about everyday situations | 98.2% | #1 / 36 |
HumanEval Coding ability - generating correct Python functions | 96.9% | #2 / 50 |
FrontierMath Unpublished research-level mathematics problems | 40.3% | #2 / 4 |
SWE-bench Real-world GitHub issue resolution | 80% | #5 / 39 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 88% | #9 / 62 |
GPQA PhD-level science questions even experts struggle with | 93.2% | #13 / 96 |
Arena Elo Human preference ranking via blind comparisons | 1458 | #19 / 51 |
ARC-AGI Novel reasoning tasks requiring fluid intelligence | 54.2% | #25 / 40 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 43.2% | #26 / 58 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 26.7% | #72 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisGPT-5.2 (Medium) | 26.7% |
MMMU-Pro Artificial AnalysisGPT-5.2 (Medium) | 74.6% |
AA-LCR Artificial AnalysisGPT-5.2 (Medium) | 70.3% |
CritPt Artificial AnalysisGPT-5.2 (Medium) | 7.9% |
IFBench Artificial AnalysisGPT-5.2 (Medium) | 65.2% |