Frontier-tier Qwen flagship. AA Intelligence Index 56.6, GPQA 92.3, Terminal-Bench 50.8 — closes the gap to Western frontier at lower cost.
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 models released within six months of it.
| Benchmark | Score | Rank |
|---|---|---|
Arena EloArtificial Analysis Human preference ranking via blind comparisons | 1545 | #5 / 51 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 89.3% | #13 / 61 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 87.1% | #17 / 62 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 50.8% | #18 / 58 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 92.3% | #24 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 40.5% | #41 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisQwen3.7 Max | 40.5% |
Terminal-Bench 2.1 Artificial AnalysisQwen3.7 Max | 74.5% |
Terminal-Bench 4.0 Artificial AnalysisQwen3.7 Max | 1.5% |
SciCode Artificial AnalysisQwen3.7 Max | 49.5% |
AA-LCR Artificial AnalysisQwen3.7 Max | 79% |
CritPt Artificial AnalysisQwen3.7 Max | 13.4% |
ITBench SRE Artificial AnalysisQwen3.7 Max | 42.5% |
IFBench Artificial AnalysisQwen3.7 Max | 80.5% |