#1 on Arena thinking mode, 1M context, strong agentic coding
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 38 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 | 93.1% | #3 / 54 |
ARC-C Grade-school science questions requiring reasoning | 98.5% | #4 / 40 |
HumanEval Coding ability - generating correct Python functions | 96.1% | #5 / 50 |
MATH Competition-level mathematics problems | 98.4% | #5 / 50 |
HellaSwag Common sense reasoning about everyday situations | 97.2% | #5 / 36 |
Arena Elo Human preference ranking via blind comparisons | 1483 | #13 / 51 |
SWE-bench Real-world GitHub issue resolution | 74.6% | #17 / 39 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 80.6% | #42 / 62 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 72.7% | #46 / 51 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 24.2% | #46 / 58 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 84.2% | #47 / 61 |
GPQA PhD-level science questions even experts struggle with | 88% | #54 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 19.3% | #79 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisGrok 4.1 Fast (Reasoning) | 19.3% |
MMMU-Pro Artificial AnalysisGrok 4.1 Fast (Reasoning) | 63.3% |
AA-LCR Artificial AnalysisGrok 4.1 Fast (Reasoning) | 74% |
CritPt Artificial AnalysisGrok 4.1 Fast (Reasoning) | 2.9% |
IFBench Artificial AnalysisGrok 4.1 Fast (Reasoning) | 52.7% |