First hybrid reasoning model, extended thinking mode for complex problems
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 21 models released within six months of it, across 7 benchmarks where scores spread out.
| Benchmark | Score | Rank |
|---|---|---|
MATH Competition-level mathematics problems | 96.2% | #14 / 50 |
HumanEval Coding ability - generating correct Python functions | 93.7% | #18 / 50 |
ARC-C Grade-school science questions requiring reasoning | 96.7% | #24 / 40 |
HellaSwag Common sense reasoning about everyday situations | 89% | #28 / 36 |
SWE-bench Real-world GitHub issue resolution | 62.3% | #29 / 39 |
Arena Elo Human preference ranking via blind comparisons | 1310 | #40 / 51 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 86.1% | #41 / 54 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 75.1% | #42 / 51 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 21.2% | #47 / 58 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 82.7% | #52 / 61 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 60.4% | #58 / 62 |
GPQA PhD-level science questions even experts struggle with | 84.8% | #62 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 4.2% | #96 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisClaude 3.7 Sonnet (Non-reasoning) | 4.2% |
MMMU-Pro Artificial AnalysisClaude 3.7 Sonnet (Non-reasoning) | 60.1% |
AA-LCR Artificial AnalysisClaude 3.7 Sonnet (Non-reasoning) | 51.7% |
CritPt Artificial AnalysisClaude 3.7 Sonnet (Non-reasoning) | 0% |
IFBench Artificial AnalysisClaude 3.7 Sonnet (Non-reasoning) | 44% |