benchgap
Other · model

Ling 3.1 Flash benchmark scores

As of 2026-11-22, Ling 3.1 Flash (Other) has measured scores on 23 benchmarks and estimated scores on 113 more.

BenchmarkScoreSource
AA-GPQA Diamond96.2%estimated ± 2.1 pp, low confidence
AA-HLE39.4%measured
AA-SciCode54.1%measured
Artificial Analysis Intelligence Index37.4%estimated ± 7.2 pp, medium confidence
CritPt18.0%measured
GDPval-AA55.9%measured
GPQA Diamond96.3%estimated ± 1.2 pp, medium confidence
HLE37.4%measured
AA-LCR83.0%measured
LiveCodeBench v692.8%estimated ± 2.7 pp, high confidence
AA-Omniscience Accuracy31.8%estimated ± 9.1 pp, medium confidence
SciCode53.8%estimated ± 3.1 pp, high confidence
Terminal-Bench 2.181.2%measured
BrowseComp91.7%measured
HLE w/ tools63.6%estimated ± 4.9 pp, medium confidence
LongBench v268.4%estimated ± 5.5 pp, medium confidence
VITA-Bench47.3%estimated ± 6.7 pp, low confidence
τ²-bench results93.6%estimated ± 11.8 pp, low confidence
AA Coding Index73.0%estimated ± 2.5 pp, high confidence
APEX-Agents65.7%estimated ± 7.4 pp, low confidence
APEX-Agents-AA43.5%estimated ± 4.4 pp, medium confidence
BioMysteryBench (human-difficult)47.6%estimated ± 6.8 pp, low confidence
DeepSearchQA93.3%estimated ± 6.8 pp, low confidence
SWE-bench Verified87.8%estimated ± 3.6 pp, high confidence
AutomationBench52.5%measured
BFCL v477.1%estimated ± 2.7 pp, medium confidence
CyberGym87.9%measured
JobBench59.1%estimated ± 5.1 pp, low confidence
SkillsBench68.7%measured
SWE-bench Pro68.7%measured
τ³-bench results47.8%measured
WideResearch83.3%measured
AA Agentic Index52.0%estimated ± 3.1 pp, high confidence
MMLU-Pro85.7%estimated ± 14.4 pp, low confidence
GPQA96.3%estimated ± 1.2 pp, medium confidence
Vals GPQA Diamond98.8%estimated ± 1.2 pp, low confidence
Vals LiveCodeBench87.1%estimated ± 4.7 pp, medium confidence
Vals MMLU-Pro85.7%estimated ± 2.4 pp, medium confidence
MMMLU90.6%estimated ± 0.7 pp, low confidence
Chess Puzzles41.5%estimated ± 10.8 pp, low confidence
AA MMLU-Pro88.9%estimated ± 1.3 pp, high confidence
Gert Labs58.6%estimated ± 5.3 pp, low confidence
AA-AnalystAgent46.7%estimated ± 3.7 pp, medium confidence
AA Harvey LAB v1.093.3%estimated ± 9.8 pp, low confidence
AA Tau3 Banking100.0%estimated ± 3.3 pp, low confidence
AA Terminal-Bench 2.181.7%estimated ± 2.6 pp, high confidence
ApprenticeBench32.5%estimated ± 4.0 pp, medium confidence
ARC-AGI-188.2%estimated ± 7.8 pp, low confidence
ARC-AGI-265.2%estimated ± 14.4 pp, low confidence
CursorBench 3.154.1%estimated ± 3.4 pp, medium confidence
CursorBench 3.266.5%estimated ± 3.6 pp, high confidence
EBR-bench33.6%estimated ± 11.3 pp, low confidence
Terminal-Bench 3.014.4%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main44.1%estimated ± 3.5 pp, low confidence
FrontierSWE v230.7%estimated ± 8.3 pp, medium confidence
Furniture Assembly37.9%estimated ± 12.4 pp, low confidence
MaxxBench51.6%estimated ± 5.7 pp, medium confidence
MazeBench7.8%estimated ± 5.5 pp, low confidence
Mystery Game Puzzles28.6%estimated ± 13.3 pp, low confidence
OSWorld-Verified80.7%estimated ± 4.7 pp, high confidence
Terminal-Bench 4.145.0%estimated ± 4.6 pp, high confidence
Vals SWE-bench89.5%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)68.5%estimated ± 7.3 pp, medium confidence
CWE-Bench-AA61.1%estimated ± 6.0 pp, low confidence
AA Cyber Index46.3%estimated ± 9.4 pp, medium confidence
DeepsecBench-AA26.4%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)56.5%estimated ± 7.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)64.2%estimated ± 0.8 pp, low confidence
AA ITBench50.7%estimated ± 4.1 pp, high confidence
Bug Hunt Bench22.1%estimated ± 10.4 pp, low confidence
CursorBench 4.042.2%estimated ± 3.3 pp, high confidence
CWE-bench v159.6%estimated ± 6.4 pp, medium confidence
DeepSWE59.7%measured
DRACO85.5%measured
FrontierCode 2.025.1%estimated ± 6.7 pp, medium confidence
FrontierPhysics2.2%estimated ± 4.7 pp, high confidence
HLE w/o tools57.0%estimated ± 4.9 pp, medium confidence
OSWorld 2.170.9%estimated ± 6.0 pp, medium confidence
OSWorld 2.1 Offline72.7%estimated ± 1.9 pp, medium confidence
PostTrainBench v1.131.4%estimated ± 4.4 pp, high confidence
StealthMark42.4%measured
SWE Multilingual88.5%measured
Terminal-Bench 4.046.0%measured
Terminal-Bench-Science 0.131.5%estimated ± 14.2 pp, low confidence
Toolathlon-Verified75.4%estimated ± 1.2 pp, medium confidence
VulcanBench Frontier v479.6%estimated ± 5.0 pp, high confidence
GDP.pdf17.0%estimated ± 4.6 pp, high confidence
AA Terminal-Bench 4.042.9%estimated ± 6.3 pp, medium confidence
ARC-AGI-30.0%estimated ± 8.3 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, medium confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
MKA41.9%estimated ± 6.4 pp, low confidence
FACTS Multimodal41.6%estimated ± 4.7 pp, high confidence
Hermes Bench72.1%estimated ± 2.9 pp, high confidence
Hermes Index44.9%estimated ± 8.7 pp, medium confidence
ExploitBench31.3%estimated ± 12.6 pp, low confidence
ExploitGym31.7%estimated ± 9.2 pp, low confidence
C-Eval94.8%estimated ± 0.9 pp, low confidence
Claw-Eval72.6%estimated ± 6.3 pp, low confidence
DeepPlanning51.5%estimated ± 13.1 pp, low confidence
INCLUDE88.8%estimated ± 2.0 pp, medium confidence
MCP Atlas83.0%measured
MMLU-ProX90.7%estimated ± 1.3 pp, medium confidence
MMLU-Redux95.7%estimated ± 2.1 pp, high confidence
NL2Repo56.4%estimated ± 6.0 pp, medium confidence
PostTrainBench v134.3%estimated ± 4.6 pp, high confidence
QwenClawBench68.4%estimated ± 2.6 pp, medium confidence
SuperGPQA77.5%estimated ± 7.2 pp, medium confidence
Toolathlon62.8%estimated ± 4.2 pp, high confidence
HealthBench Hard32.1%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro90.1%estimated ± 6.0 pp, low confidence
React Native Evals78.4%estimated ± 4.7 pp, medium confidence
ResearchClawBench19.6%estimated ± 1.8 pp, high confidence
PostTrainBench28.9%estimated ± 3.7 pp, high confidence
DAYJOB2.1%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.9%estimated ± 4.7 pp, high confidence
Finance Agent v257.9%measured
BioMysteryBench (human-solvable)88.8%estimated ± 0.6 pp, medium confidence
FrontierCode 1.1 Extended58.6%estimated ± 3.0 pp, medium confidence
HealthBench (raw)48.2%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)60.3%estimated ± 2.2 pp, high confidence
HealthBench Professional65.4%measured
HealthBench Professional (raw)58.8%estimated ± 4.5 pp, high confidence
HLE-Verified3.6%estimated ± 6.8 pp, low confidence
LABBench279.5%estimated ± 2.4 pp, low confidence
ScarfBench63.0%estimated ± 3.8 pp, medium confidence
Agents' Last Exam29.9%estimated ± 3.1 pp, high confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
SEC-Bench Pro49.7%estimated ± 9.3 pp, medium confidence
MRCRv285.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.5%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, medium confidence
LifeVal80.5%estimated ± 1.6 pp, medium confidence
ExploitBench Internal Port0.0%estimated ± 6.8 pp, low confidence
PinchBench90.8%estimated ± 3.6 pp, low confidence
SWE-Atlas Codebase QnA64.5%measured