benchgap
Other · model

LongCat-Flash-Lite-Sparse benchmark scores

As of 2026-11-22, LongCat-Flash-Lite-Sparse (Other) has measured scores on 15 benchmarks and estimated scores on 76 more.

BenchmarkScoreSource
AA-GPQA Diamond67.2%estimated ± 4.4 pp, high confidence
AA-HLE9.1%estimated ± 3.9 pp, high confidence
AA-SciCode40.3%estimated ± 3.6 pp, high confidence
AIME2665.7%measured
Artificial Analysis Intelligence Index9.8%estimated ± 3.2 pp, medium confidence
CritPt0.0%estimated ± 4.1 pp, medium confidence
GDPval-AA19.3%estimated ± 7.8 pp, medium confidence
GPQA Diamond69.5%measured
HLE8.2%estimated ± 6.8 pp, medium confidence
LiveCodeBench v681.9%estimated ± 2.7 pp, high confidence
AA-Omniscience Accuracy16.5%estimated ± 2.4 pp, high confidence
SciCode42.1%estimated ± 3.6 pp, high confidence
BrowseComp48.6%measured
HLE w/ tools36.2%estimated ± 5.6 pp, medium confidence
VITA-Bench21.7%measured
τ²-bench results77.5%estimated ± 11.8 pp, low confidence
AA Coding Index37.3%estimated ± 5.3 pp, medium confidence
APEX-Agents2.5%estimated ± 12.6 pp, low confidence
APEX-Agents-AA7.9%estimated ± 4.4 pp, medium confidence
DeepSearchQA75.1%estimated ± 6.8 pp, low confidence
SWE-bench Verified68.2%measured
BFCL v467.8%estimated ± 4.7 pp, low confidence
CyberGym34.5%estimated ± 7.3 pp, low confidence
JobBench23.2%estimated ± 7.9 pp, medium confidence
SWE-bench Pro40.6%measured
WideResearch59.1%estimated ± 3.5 pp, medium confidence
AA Agentic Index12.2%estimated ± 8.2 pp, medium confidence
MMLU-Pro79.2%measured
AIME 202475.0%estimated ± 7.1 pp, medium confidence
BBH90.2%estimated ± 2.4 pp, low confidence
GPQA69.3%estimated ± 1.2 pp, high confidence
MMLU85.3%measured
Vals GPQA Diamond59.8%estimated ± 8.2 pp, medium confidence
Vals LiveCodeBench57.8%estimated ± 4.7 pp, low confidence
Vals MMLU-Pro72.4%estimated ± 2.4 pp, high confidence
MATH-50095.8%measured
MMMLU73.6%estimated ± 1.1 pp, low confidence
AIME 202557.0%estimated ± 1.8 pp, medium confidence
Gert Labs28.9%estimated ± 11.1 pp, low confidence
AA Harvey LAB v1.082.4%estimated ± 9.8 pp, low confidence
CursorBench 3.140.6%estimated ± 5.6 pp, low confidence
CursorBench 3.218.7%estimated ± 3.6 pp, medium confidence
FrontierCode 1.1 Main6.7%estimated ± 4.2 pp, low confidence
FrontierSWE v20.0%estimated ± 8.3 pp, low confidence
MazeBench0.0%estimated ± 6.4 pp, low confidence
OSWorld-Verified51.0%estimated ± 5.7 pp, low confidence
Terminal-Bench Hard41.2%estimated ± 4.0 pp, medium confidence
Vals SWE-bench60.3%estimated ± 6.6 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)28.8%estimated ± 6.4 pp, low confidence
CWE-Bench-AA34.2%estimated ± 6.4 pp, medium confidence
AA Cyber Index25.3%estimated ± 13.5 pp, low confidence
AA ITBench30.6%estimated ± 4.1 pp, medium confidence
Bug Hunt Bench22.3%estimated ± 12.1 pp, low confidence
CursorBench 4.021.0%estimated ± 3.3 pp, medium confidence
DeepSWE38.9%estimated ± 11.2 pp, low confidence
DRACO55.9%estimated ± 4.0 pp, low confidence
FrontierCode 2.018.2%estimated ± 6.7 pp, low confidence
HLE w/o tools9.2%estimated ± 4.3 pp, medium confidence
PostTrainBench v1.115.3%estimated ± 4.4 pp, medium confidence
SWE Multilingual59.3%measured
Toolathlon-Verified33.1%estimated ± 7.4 pp, low confidence
VulcanBench Frontier v466.3%estimated ± 8.3 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, medium confidence
C-Eval85.8%measured
Claw-Eval61.6%estimated ± 6.3 pp, low confidence
DeepPlanning26.2%estimated ± 9.1 pp, low confidence
HMMT Feb 202640.5%measured
INCLUDE80.7%estimated ± 2.0 pp, low confidence
MCP Atlas45.6%measured
MCP-Tasks73.5%estimated ± 0.6 pp, medium confidence
MMLU-ProX81.4%estimated ± 1.3 pp, medium confidence
MMLU-Redux89.9%estimated ± 0.6 pp, high confidence
NL2Repo23.3%estimated ± 6.1 pp, low confidence
PostTrainBench v15.1%estimated ± 4.6 pp, medium confidence
QwenClawBench52.0%estimated ± 2.0 pp, low confidence
SuperGPQA60.6%estimated ± 12.4 pp, low confidence
Terminal-Bench 2.033.7%measured
Toolathlon23.8%estimated ± 4.2 pp, medium confidence
LiveCodeBench Pro66.2%estimated ± 6.0 pp, low confidence
MMLU-Pro (Arcee)78.7%estimated ± 3.4 pp, medium confidence
React Native Evals74.3%estimated ± 2.7 pp, medium confidence
ResearchClawBench15.8%estimated ± 1.8 pp, high confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
PostTrainBench14.1%estimated ± 3.7 pp, medium confidence
FrontierCode 1.1 Extended47.9%estimated ± 3.0 pp, low confidence
SimpleQA31.2%estimated ± 11.7 pp, low confidence
LiveCodeBench71.8%estimated ± 14.6 pp, low confidence
OpenHarmony Bench v1.053.3%estimated ± 4.9 pp, low confidence
IMOAnswerBench49.4%measured
LifeVal15.0%estimated ± 1.6 pp, low confidence
PinchBench87.5%estimated ± 3.6 pp, medium confidence