Flash-tier model outperforming previous-gen Pro on most benchmarks
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 10 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
ARC-C Grade-school science questions requiring reasoning | 98.4% | #6 / 40 |
HellaSwag Common sense reasoning about everyday situations | 97.1% | #6 / 36 |
HumanEval Coding ability - generating correct Python functions | 94.8% | #12 / 50 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 87.6% | #13 / 51 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 91.2% | #16 / 54 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 88.6% | #18 / 61 |
MATH Competition-level mathematics problems | 94.6% | #19 / 50 |
SWE-bench Real-world GitHub issue resolution | 72% | #24 / 39 |
Arena Elo Human preference ranking via blind comparisons | 1428 | #24 / 51 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 85.6% | #26 / 62 |
ARC-AGIARC Prize Novel reasoning tasks requiring fluid intelligence | 34% | #30 / 40 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 38.6% | #33 / 58 |
GPQA PhD-level science questions even experts struggle with | 90.4% | #38 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 36.6% | #52 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisGemini 3 Flash Preview (Reasoning) | 36.6% |
MMMU-Pro Artificial AnalysisGemini 3 Flash Preview (Reasoning) | 79.9% |
AA-LCR Artificial AnalysisGemini 3 Flash Preview (Reasoning) | 78% |
CritPt Artificial AnalysisGemini 3 Flash Preview (Reasoning) | 8.6% |
IFBench Artificial AnalysisGemini 3 Flash Preview (Reasoning) | 78% |