benchgap
Other · model

dots3-note Preview benchmark scores

As of 2026-11-21, dots3-note Preview (Other) has measured scores on 28 benchmarks and estimated scores on 107 more.

BenchmarkScoreSource
AA-GPQA Diamond93.2%estimated ± 2.7 pp, high confidence
AA-HLE47.7%estimated ± 6.0 pp, medium confidence
AA-SciCode50.1%estimated ± 3.1 pp, high confidence
AIME2699.3%estimated ± 10.8 pp, low confidence
Artificial Analysis Intelligence Index46.2%estimated ± 8.3 pp, medium confidence
CritPt23.5%estimated ± 5.1 pp, medium confidence
GDPval-AA31.4%estimated ± 5.6 pp, medium confidence
GPQA Diamond94.0%estimated ± 1.5 pp, high confidence
HLE52.6%measured
IFBench80.4%measured
LiveCodeBench v691.5%measured
AA-Omniscience Accuracy51.9%estimated ± 7.4 pp, medium confidence
SciCode46.9%estimated ± 3.6 pp, high confidence
Terminal-Bench 2.175.1%measured
BrowseComp83.3%measured
HLE w/ tools52.6%measured
IFEval93.9%measured
VITA-Bench45.8%estimated ± 6.7 pp, low confidence
τ²-bench results97.4%estimated ± 3.1 pp, high confidence
AA Coding Index68.1%estimated ± 4.3 pp, high confidence
AA-MMMU-Pro78.2%estimated ± 1.5 pp, high confidence
APEX-Agents30.8%measured
APEX-Agents-AA30.9%estimated ± 4.4 pp, high confidence
DeepSearchQA92.1%measured
SWE-bench Verified78.4%measured
AutomationBench31.0%estimated ± 7.4 pp, low confidence
CyberGym76.7%estimated ± 7.3 pp, medium confidence
JobBench39.2%estimated ± 5.1 pp, low confidence
SkillsBench52.8%measured
SWE-bench Pro61.0%measured
WideResearch78.9%measured
AA Agentic Index26.5%estimated ± 3.3 pp, medium confidence
AA-IFBench80.4%estimated ± 7.4 pp, medium confidence
GPQA94.0%estimated ± 1.6 pp, high confidence
Vals GPQA Diamond93.0%estimated ± 2.3 pp, high confidence
Vals LiveCodeBench86.1%estimated ± 3.4 pp, medium confidence
Vals MMLU-Pro89.0%estimated ± 1.9 pp, high confidence
MMMU85.8%estimated ± 1.7 pp, high confidence
Gert Labs54.5%estimated ± 6.1 pp, low confidence
AA EnterpriseOps-Gym45.7%estimated ± 2.3 pp, medium confidence
AA Harvey LAB v1.088.7%estimated ± 1.7 pp, medium confidence
AA Tau3 Banking38.2%estimated ± 3.6 pp, medium confidence
AA Terminal-Bench 2.181.7%estimated ± 2.6 pp, high confidence
ApprenticeBench23.1%estimated ± 10.1 pp, low confidence
ARC-AGI-195.2%estimated ± 1.7 pp, high confidence
ARC-AGI-281.4%measured
CursorBench 3.155.3%estimated ± 5.6 pp, low confidence
CursorBench 3.259.4%estimated ± 3.6 pp, high confidence
Terminal-Bench 3.010.3%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main24.7%estimated ± 4.2 pp, low confidence
FrontierSWE v217.3%estimated ± 8.3 pp, medium confidence
MazeBench0.0%estimated ± 6.4 pp, low confidence
OSWorld-Verified73.3%estimated ± 3.8 pp, medium confidence
ParseBench-166.9%estimated ± 1.0 pp, medium confidence
Terminal-Bench 4.112.4%estimated ± 10.9 pp, low confidence
Vals SWE-bench83.5%estimated ± 5.2 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)63.9%estimated ± 7.3 pp, medium confidence
CWE-Bench-AA53.8%estimated ± 5.2 pp, medium confidence
AA Cyber Index35.2%estimated ± 12.8 pp, low confidence
DeepsecBench-AA16.6%estimated ± 9.0 pp, low confidence
AA ITBench47.2%estimated ± 4.1 pp, high confidence
Bug Hunt Bench16.1%estimated ± 7.2 pp, low confidence
CursorBench 4.036.3%estimated ± 3.3 pp, medium confidence
DeepSWE49.6%estimated ± 8.7 pp, medium confidence
DRACO80.1%estimated ± 2.9 pp, medium confidence
FrontierCode 2.021.5%estimated ± 6.7 pp, medium confidence
HLE w/o tools44.1%estimated ± 6.0 pp, medium confidence
OSWorld 2.167.1%estimated ± 7.2 pp, low confidence
PostTrainBench v1.126.3%estimated ± 4.4 pp, high confidence
SWE Multilingual75.7%measured
Toolathlon-Verified55.6%measured
VulcanBench Frontier v480.3%estimated ± 8.3 pp, low confidence
AA AutomationBench41.9%estimated ± 7.9 pp, low confidence
GDP.pdf12.3%estimated ± 6.1 pp, low confidence
AA Terminal-Bench 4.04.3%estimated ± 11.0 pp, low confidence
ARC-AGI-30.0%estimated ± 8.3 pp, medium confidence
Vibe Code Bench26.0%estimated ± 8.4 pp, medium confidence
Hermes Bench69.1%estimated ± 1.8 pp, medium confidence
Hermes Index34.0%estimated ± 9.3 pp, low confidence
ParseBench-270.7%estimated ± 5.0 pp, medium confidence
CharXiv89.4%estimated ± 2.4 pp, high confidence
CharXiv w/o tools83.1%measured
ExploitGym10.7%estimated ± 9.2 pp, low confidence
AI2D_TEST93.7%estimated ± 1.0 pp, medium confidence
Claw-Eval73.4%measured
CountBench97.3%estimated ± 1.3 pp, medium confidence
DynaMath85.5%estimated ± 4.1 pp, medium confidence
ERQA68.1%estimated ± 2.9 pp, medium confidence
HMMT Feb 202697.5%estimated ± 8.9 pp, low confidence
INCLUDE85.2%estimated ± 2.0 pp, medium confidence
MathVision87.7%measured
MCP Atlas82.6%estimated ± 6.6 pp, low confidence
MCP-Tasks79.1%estimated ± 6.0 pp, low confidence
MLVU (M-Avg)86.4%estimated ± 1.5 pp, high confidence
MMLU-ProX85.1%estimated ± 1.3 pp, high confidence
MMLU-Redux96.8%estimated ± 2.1 pp, medium confidence
MMMU-Pro79.1%measured
NL2Repo49.8%measured
OmniDocBench 1.590.0%estimated ± 2.0 pp, medium confidence
PostTrainBench v126.3%estimated ± 4.6 pp, high confidence
RealWorldQA86.9%estimated ± 1.8 pp, medium confidence
ScreenSpot Pro80.5%estimated ± 3.6 pp, medium confidence
SimpleVQA72.5%measured
SuperGPQA91.7%estimated ± 7.2 pp, medium confidence
Toolathlon53.0%estimated ± 4.2 pp, high confidence
Video-MME (w/o subtitle)85.0%estimated ± 1.3 pp, high confidence
Video-MME (with subtitle)87.4%estimated ± 1.9 pp, high confidence
VideoMMMU86.8%measured
We-Math87.5%estimated ± 2.1 pp, medium confidence
LiveCodeBench Pro84.5%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)72.6%estimated ± 2.4 pp, high confidence
React Native Evals78.9%estimated ± 2.7 pp, medium confidence
ResearchClawBench21.0%estimated ± 1.3 pp, medium confidence
SWE-Rebench61.6%estimated ± 3.6 pp, medium confidence
PostTrainBench24.3%estimated ± 3.7 pp, high confidence
FrontierCode 1.1 Extended56.3%estimated ± 3.0 pp, low confidence
HealthBench Professional59.0%estimated ± 4.3 pp, medium confidence
HLE-Verified51.4%estimated ± 1.3 pp, low confidence
LABBench281.2%estimated ± 3.1 pp, low confidence
LiveCodeBench78.3%estimated ± 14.6 pp, low confidence
Agents' Last Exam31.5%estimated ± 11.6 pp, low confidence
BabyVision w/ Python83.3%estimated ± 2.0 pp, low confidence
OpenHarmony Bench v1.056.3%estimated ± 2.7 pp, high confidence
IMOAnswerBench90.9%measured
BabyVision50.0%measured
MMVU79.9%measured
PerceptionBench53.4%measured
ZeroBench19.0%measured
LVBench76.1%estimated ± 8.2 pp, low confidence
OCRBench V272.0%estimated ± 2.1 pp, medium confidence
BioBasicsBench34.3%estimated ± 5.1 pp, low confidence
LifeVal74.7%estimated ± 1.6 pp, medium confidence
MMMU-Pro w/ Python81.3%estimated ± 2.6 pp, high confidence
MathVision w/ Python93.8%estimated ± 0.5 pp, low confidence
PinchBench90.4%estimated ± 3.6 pp, low confidence