Qwen efficiency tier at AA Intelligence Index 55.8, within striking distance of the 58.1 flagship.
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.
| Benchmark | Score | Rank |
|---|---|---|
aaAgentic | 56.4% | #7 / 16 |
AA Coding (Historical) Archived release-era coding composite, excluded from current rankings because comparable current-series coverage is unavailable | 73.1% | #12 / 22 |
AA Intelligence (Historical) Archived release-era composite, not comparable to the current versioned Intelligence Index used for rankings | 55.8% | #13 / 22 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 92.3% | #25 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 38% | #49 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisQwen3.8-Flash-Next | 38% |
MMMU-Pro Artificial AnalysisQwen3.8-Flash-Next | 79.8% |
Terminal-Bench 2.1 Artificial AnalysisQwen3.8-Flash-Next | 86.1% |
Terminal-Bench 4.0 Artificial AnalysisQwen3.8-Flash-Next | 25.3% |
SciCode Artificial AnalysisQwen3.8-Flash-Next | 50.6% |
AA-LCR Artificial AnalysisQwen3.8-Flash-Next | 79.7% |
CritPt Artificial AnalysisQwen3.8-Flash-Next | 11.1% |