benchgap
Other · model

Hy3 benchmark scores

As of 2026-11-21, Hy3 (Other) has measured scores on 11 benchmarks and estimated scores on 103 more.

BenchmarkScoreSource
AA-GPQA Diamond89.7%measured
AA-HLE33.5%measured
AA-SciCode48.6%measured
Artificial Analysis Intelligence Index20.0%estimated ± 7.2 pp, medium confidence
CritPt4.9%measured
GDPval-AA28.2%measured
GPQA Diamond89.2%estimated ± 2.4 pp, high confidence
HLE36.2%estimated ± 8.5 pp, medium confidence
AA-LCR79.0%measured
LiveCodeBench v686.6%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy38.4%estimated ± 7.7 pp, medium confidence
SciCode48.5%estimated ± 3.1 pp, high confidence
BrowseComp75.1%estimated ± 9.0 pp, medium confidence
HLE w/ tools47.4%estimated ± 5.3 pp, medium confidence
LongBench v264.8%estimated ± 5.5 pp, medium confidence
AA Coding Index58.8%measured
APEX-Agents20.8%estimated ± 9.4 pp, low confidence
APEX-Agents-AA23.5%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)37.0%estimated ± 6.8 pp, low confidence
DeepSearchQA87.4%estimated ± 4.5 pp, high confidence
SWE-bench Verified78.4%estimated ± 6.3 pp, medium confidence
BFCL v474.1%estimated ± 2.7 pp, high confidence
CyberGym65.3%estimated ± 5.3 pp, medium confidence
JobBench26.2%estimated ± 8.7 pp, medium confidence
SWE-bench Pro57.6%estimated ± 6.0 pp, medium confidence
WideResearch76.3%estimated ± 7.8 pp, low confidence
AA Agentic Index25.6%measured
MMLU-Pro84.9%estimated ± 7.0 pp, medium confidence
FailureSensorIQ64.5%estimated ± 1.7 pp, high confidence
GPQA90.2%estimated ± 6.1 pp, medium confidence
MMLU88.2%estimated ± 8.3 pp, low confidence
Vals GPQA Diamond88.8%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench82.6%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro87.1%estimated ± 3.0 pp, high confidence
MMMLU88.4%estimated ± 0.7 pp, medium confidence
Chess Puzzles37.0%estimated ± 11.1 pp, low confidence
AA MMLU-Pro88.9%estimated ± 1.3 pp, high confidence
Gert Labs56.9%estimated ± 8.3 pp, medium confidence
AA Harvey LAB v1.084.3%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking30.7%estimated ± 3.7 pp, high confidence
ARC-AGI-178.4%estimated ± 7.8 pp, low confidence
ARC-AGI-240.0%estimated ± 14.4 pp, low confidence
BabaIsBench54.0%measured
CursorBench 3.140.6%estimated ± 3.4 pp, low confidence
CursorBench 3.243.9%estimated ± 4.4 pp, medium confidence
EBR-bench17.8%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main26.9%estimated ± 4.6 pp, high confidence
FrontierSWE v215.9%estimated ± 14.2 pp, low confidence
MaxxBench38.8%estimated ± 11.1 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
Mystery Game Puzzles27.0%estimated ± 9.8 pp, medium confidence
NYT Connections41.2%measured
OSWorld-Verified70.3%estimated ± 8.4 pp, low confidence
Vals SWE-bench77.3%estimated ± 5.5 pp, medium confidence
CWE-Bench-AA35.7%estimated ± 10.1 pp, low confidence
AA Cyber Index16.8%estimated ± 9.2 pp, low confidence
DeepsecBench-AA2.5%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.9%estimated ± 7.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)41.4%estimated ± 0.8 pp, low confidence
AA ITBench41.0%estimated ± 4.0 pp, high confidence
Bug Hunt Bench7.5%estimated ± 9.0 pp, low confidence
CursorBench 4.034.9%estimated ± 4.9 pp, medium confidence
CWE-bench v137.7%estimated ± 6.4 pp, low confidence
DeepSWE30.4%estimated ± 6.4 pp, low confidence
DRACO74.9%estimated ± 2.0 pp, medium confidence
FrontierCode 2.026.1%estimated ± 9.3 pp, low confidence
HLE w/o tools33.0%estimated ± 5.4 pp, medium confidence
OSWorld 2.143.4%estimated ± 6.0 pp, low confidence
OSWorld 2.1 Offline4.9%estimated ± 1.9 pp, low confidence
PostTrainBench v1.114.6%estimated ± 5.7 pp, low confidence
SpireClimb5.8%estimated ± 7.2 pp, low confidence
StealthMark41.3%estimated ± 10.7 pp, low confidence
Toolathlon-Verified55.3%estimated ± 2.3 pp, medium confidence
VulcanBench Frontier v478.8%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
MKA23.6%estimated ± 6.4 pp, low confidence
SkillsBench official leaderboard (BenchFlow)55.9%measured
BinaryAudit40.8%estimated ± 12.0 pp, low confidence
OTelBench22.4%estimated ± 6.6 pp, medium confidence
Vibe Code Bench32.0%estimated ± 10.0 pp, low confidence
FACTS Multimodal24.7%estimated ± 4.0 pp, medium confidence
Hermes Bench58.5%estimated ± 2.9 pp, high confidence
Hermes Index25.5%estimated ± 8.7 pp, medium confidence
ExploitGym1.8%estimated ± 10.6 pp, low confidence
C-Eval95.6%estimated ± 1.1 pp, low confidence
MCP Atlas78.3%estimated ± 7.8 pp, low confidence
MMLU-Redux95.0%estimated ± 3.3 pp, high confidence
NL2Repo42.7%estimated ± 4.7 pp, high confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
Toolathlon52.9%estimated ± 6.3 pp, medium confidence
AA LiveCodeBench88.1%estimated ± 4.7 pp, low confidence
HealthBench Hard23.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)95.5%estimated ± 4.0 pp, low confidence
React Native Evals78.9%estimated ± 3.2 pp, high confidence
ResearchClawBench17.9%estimated ± 1.9 pp, high confidence
SWE-Rebench58.1%estimated ± 8.9 pp, low confidence
DAYJOB1.4%estimated ± 5.5 pp, low confidence
BioMysteryBench (human-solvable)81.8%estimated ± 0.6 pp, low confidence
HealthBench (raw)42.5%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)51.1%estimated ± 3.4 pp, low confidence
HealthBench Professional58.1%estimated ± 4.5 pp, low confidence
HealthBench Professional (raw)53.5%estimated ± 4.5 pp, medium confidence
HLE-Verified16.8%estimated ± 2.0 pp, low confidence
LABBench276.6%estimated ± 1.8 pp, low confidence
ScarfBench25.9%estimated ± 9.1 pp, low confidence
SimpleQA33.5%estimated ± 7.8 pp, low confidence
OpenHarmony Bench v1.051.3%estimated ± 2.4 pp, high confidence
MRCRv285.6%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.4%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
ExploitBench Internal Port0.2%estimated ± 13.8 pp, low confidence