benchgap
Other · model

Ling 3.0 Flash VL benchmark scores

As of 2026-11-22, Ling 3.0 Flash VL (Other) has measured scores on 7 benchmarks and estimated scores on 106 more.

BenchmarkScoreSource
AA-GPQA Diamond86.2%measured
AA-HLE22.0%measured
AA-SciCode44.2%measured
Artificial Analysis Intelligence Index15.7%estimated ± 7.2 pp, medium confidence
CritPt2.0%measured
GDPval-AA33.0%measured
GPQA Diamond82.7%estimated ± 2.4 pp, high confidence
HLE24.7%estimated ± 8.5 pp, medium confidence
AA-LCR78.3%measured
LiveCodeBench v684.8%estimated ± 4.9 pp, high confidence
AA-Omniscience Accuracy31.2%estimated ± 7.7 pp, medium confidence
SciCode44.2%estimated ± 3.1 pp, high confidence
BrowseComp75.5%estimated ± 9.2 pp, medium confidence
HLE w/ tools49.7%estimated ± 5.3 pp, medium confidence
LongBench v264.2%estimated ± 5.5 pp, medium confidence
AA Coding Index48.5%estimated ± 6.1 pp, medium confidence
AA-MMMU-Pro79.0%measured
APEX-Agents25.1%estimated ± 9.4 pp, low confidence
APEX-Agents-AA26.5%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)25.6%estimated ± 6.8 pp, low confidence
DeepSearchQA87.7%estimated ± 9.6 pp, medium confidence
SWE-bench Verified72.0%estimated ± 6.3 pp, medium confidence
BFCL v474.9%estimated ± 2.7 pp, medium confidence
CyberGym63.8%estimated ± 6.0 pp, medium confidence
JobBench32.2%estimated ± 8.7 pp, medium confidence
SWE-bench Pro49.8%estimated ± 6.3 pp, medium confidence
WideResearch78.5%estimated ± 7.8 pp, low confidence
AA Agentic Index26.5%estimated ± 3.1 pp, high confidence
MMLU-Pro84.6%estimated ± 7.0 pp, medium confidence
GPQA87.0%estimated ± 6.1 pp, medium confidence
MMLU88.2%estimated ± 8.3 pp, low confidence
Vals GPQA Diamond85.3%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench79.7%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro86.0%estimated ± 3.0 pp, high confidence
MMMLU87.2%estimated ± 0.7 pp, medium confidence
MMMU85.9%estimated ± 2.7 pp, high confidence
AA MMLU-Pro85.7%estimated ± 1.3 pp, high confidence
Gert Labs37.5%estimated ± 10.0 pp, low confidence
AA Tau3 Banking35.2%estimated ± 4.1 pp, high confidence
ARC-AGI-176.2%estimated ± 7.8 pp, low confidence
ARC-AGI-234.4%estimated ± 14.4 pp, low confidence
CursorBench 3.129.7%estimated ± 3.4 pp, low confidence
CursorBench 3.244.4%estimated ± 5.3 pp, low confidence
FrontierCode 1.1 Main0.1%estimated ± 6.6 pp, low confidence
FrontierSWE v29.6%estimated ± 14.2 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OfficeQA Pro51.4%estimated ± 6.8 pp, medium confidence
OSWorld-Verified72.9%estimated ± 8.4 pp, low confidence
ParseBench-164.0%estimated ± 6.2 pp, medium confidence
Vals SWE-bench69.8%estimated ± 8.2 pp, medium confidence
CWE-Bench-AA40.1%estimated ± 10.1 pp, low confidence
DeepsecBench-AA5.8%estimated ± 8.9 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)8.9%estimated ± 2.1 pp, low confidence
AA ITBench41.1%estimated ± 5.1 pp, low confidence
Bug Hunt Bench17.5%estimated ± 10.5 pp, low confidence
Chartography (tools)82.8%estimated ± 4.1 pp, low confidence
CursorBench 4.030.5%estimated ± 4.9 pp, medium confidence
CWE-bench v142.3%estimated ± 6.4 pp, medium confidence
DeepSWE43.8%estimated ± 7.5 pp, low confidence
DRACO77.7%estimated ± 2.0 pp, medium confidence
FrontierCode 2.026.1%estimated ± 9.3 pp, low confidence
HLE w/o tools21.0%estimated ± 5.4 pp, medium confidence
OSWorld 2.148.9%estimated ± 6.0 pp, low confidence
OSWorld 2.1 Offline11.5%estimated ± 1.9 pp, low confidence
PostTrainBench v1.126.6%estimated ± 7.4 pp, low confidence
Toolathlon-Verified59.3%estimated ± 3.1 pp, high confidence
VulcanBench Frontier v474.3%estimated ± 6.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
MKA27.1%estimated ± 6.4 pp, low confidence
Hermes Bench61.9%estimated ± 2.9 pp, high confidence
Hermes Index29.2%estimated ± 8.7 pp, medium confidence
ParseBench-270.3%estimated ± 6.2 pp, medium confidence
CharXiv83.4%estimated ± 6.3 pp, low confidence
CharXiv w/o tools82.7%estimated ± 2.5 pp, high confidence
ExploitGym4.2%estimated ± 10.6 pp, low confidence
AI2D_TEST94.1%estimated ± 2.0 pp, medium confidence
C-Eval92.7%estimated ± 1.1 pp, medium confidence
CountBench97.5%estimated ± 2.9 pp, medium confidence
DynaMath85.5%estimated ± 3.0 pp, medium confidence
ERQA68.5%estimated ± 3.1 pp, high confidence
MathVision89.6%estimated ± 3.1 pp, high confidence
MCP Atlas73.1%estimated ± 10.7 pp, low confidence
MMLU-Redux93.9%estimated ± 3.3 pp, high confidence
MMMU-Pro79.7%estimated ± 1.5 pp, high confidence
NL2Repo39.5%estimated ± 7.4 pp, medium confidence
QwenClawBench85.4%estimated ± 6.0 pp, low confidence
RealWorldQA85.5%estimated ± 2.9 pp, medium confidence
ScreenSpot Pro76.9%estimated ± 10.8 pp, low confidence
Toolathlon55.7%estimated ± 6.3 pp, medium confidence
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)85.9%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)87.6%estimated ± 3.7 pp, medium confidence
HealthBench Hard15.3%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)76.5%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)84.6%estimated ± 4.0 pp, medium confidence
React Native Evals74.2%estimated ± 4.7 pp, medium confidence
ResearchClawBench17.4%estimated ± 2.2 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)30.1%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)46.7%estimated ± 3.4 pp, low confidence
HealthBench Professional58.1%estimated ± 4.5 pp, low confidence
HealthBench Professional (raw)41.9%estimated ± 4.5 pp, medium confidence
ScarfBench43.2%estimated ± 14.0 pp, low confidence
SimpleQA31.7%estimated ± 7.8 pp, low confidence
BabyVision w/ Python90.2%estimated ± 4.0 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
MRCRv285.5%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.3%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
MMMU-Pro w/ Python81.8%estimated ± 2.0 pp, high confidence