benchgap
Other · model

Ornith-1.5-9B benchmark scores

As of 2026-11-22, Ornith-1.5-9B (Other) has measured scores on 15 benchmarks and estimated scores on 80 more.

BenchmarkScoreSource
AA-GPQA Diamond83.9%estimated ± 2.7 pp, high confidence
AA-HLE27.3%estimated ± 3.9 pp, high confidence
AA-SciCode42.2%estimated ± 3.1 pp, high confidence
Artificial Analysis Intelligence Index8.7%estimated ± 5.6 pp, medium confidence
CritPt2.6%estimated ± 4.0 pp, high confidence
GDPval-AA19.6%estimated ± 5.6 pp, low confidence
GPQA Diamond86.4%measured
HLE20.2%measured
LiveCodeBench v680.7%estimated ± 1.7 pp, medium confidence
AA-Omniscience Accuracy20.1%estimated ± 7.7 pp, medium confidence
SciCode43.2%estimated ± 3.6 pp, high confidence
Terminal-Bench 2.146.2%measured
BrowseComp56.4%measured
HLE w/ tools30.5%measured
VITA-Bench27.3%estimated ± 6.7 pp, low confidence
τ²-bench results65.2%estimated ± 3.1 pp, medium confidence
AA Coding Index46.1%estimated ± 4.3 pp, high confidence
APEX-Agents32.1%estimated ± 12.4 pp, low confidence
APEX-Agents-AA9.6%estimated ± 4.4 pp, medium confidence
DeepSearchQA76.1%estimated ± 6.8 pp, low confidence
SWE-bench Verified70.6%measured
BFCL v468.9%estimated ± 4.7 pp, low confidence
CyberGym42.2%estimated ± 7.3 pp, low confidence
JobBench29.3%estimated ± 7.9 pp, medium confidence
SkillsBench30.2%estimated ± 4.1 pp, low confidence
SWE-bench Pro47.5%measured
WideResearch59.5%measured
AA Agentic Index7.7%estimated ± 3.3 pp, low confidence
MMLU-Pro84.4%estimated ± 2.5 pp, medium confidence
GPQA86.4%measured
MMLU88.1%estimated ± 4.2 pp, medium confidence
Vals GPQA Diamond85.7%estimated ± 2.1 pp, high confidence
Vals LiveCodeBench73.5%estimated ± 4.7 pp, medium confidence
Vals MMLU-Pro83.5%estimated ± 0.9 pp, medium confidence
MMMLU88.4%estimated ± 1.1 pp, medium confidence
AA MMLU-Pro86.6%estimated ± 1.2 pp, low confidence
Gert Labs18.5%estimated ± 5.3 pp, low confidence
AA Harvey LAB v1.077.1%estimated ± 1.7 pp, low confidence
AA Tau3 Banking21.0%estimated ± 3.6 pp, low confidence
ARC-AGI-183.4%estimated ± 2.5 pp, medium confidence
ARC-AGI-237.3%estimated ± 9.7 pp, low confidence
CursorBench 3.145.9%estimated ± 5.6 pp, low confidence
CursorBench 3.234.5%estimated ± 3.6 pp, medium confidence
Terminal-Bench 3.03.1%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main10.9%estimated ± 4.2 pp, low confidence
FrontierSWE v20.0%estimated ± 8.3 pp, low confidence
MazeBench0.0%estimated ± 6.4 pp, low confidence
OSWorld-Verified71.9%estimated ± 3.8 pp, medium confidence
Terminal-Bench 4.10.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench66.1%estimated ± 5.2 pp, low confidence
Terminal-Bench 2.1 (Vals AI)42.0%estimated ± 7.3 pp, low confidence
CWE-Bench-AA14.6%estimated ± 5.2 pp, low confidence
AA Cyber Index22.0%estimated ± 12.8 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.5%estimated ± 4.4 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)50.4%estimated ± 2.6 pp, low confidence
AA ITBench34.6%estimated ± 4.1 pp, medium confidence
Bug Hunt Bench7.5%estimated ± 7.2 pp, low confidence
CursorBench 4.026.1%estimated ± 3.3 pp, medium confidence
DeepSWE28.0%estimated ± 8.7 pp, low confidence
DRACO57.0%estimated ± 2.9 pp, low confidence
FrontierCode 2.018.7%estimated ± 6.7 pp, low confidence
HLE w/o tools20.2%measured
PostTrainBench v1.118.6%estimated ± 4.4 pp, medium confidence
SWE Multilingual54.4%measured
Toolathlon-Verified41.2%measured
VulcanBench Frontier v471.7%estimated ± 8.3 pp, low confidence
ARC-AGI-30.1%estimated ± 7.2 pp, low confidence
Vibe Code Bench0.1%estimated ± 8.4 pp, medium confidence
C-Eval89.6%estimated ± 0.9 pp, low confidence
Claw-Eval66.5%measured
DeepPlanning36.9%estimated ± 13.1 pp, low confidence
INCLUDE79.3%estimated ± 2.0 pp, low confidence
MCP Atlas54.2%measured
MCP-Tasks75.8%estimated ± 0.6 pp, low confidence
MMLU-Redux94.1%estimated ± 1.7 pp, high confidence
NL2Repo32.4%measured
PostTrainBench v112.2%estimated ± 4.6 pp, medium confidence
QwenClawBench54.6%estimated ± 2.6 pp, high confidence
SuperGPQA61.3%estimated ± 7.2 pp, medium confidence
Toolathlon29.2%estimated ± 4.2 pp, medium confidence
LiveCodeBench Pro73.1%estimated ± 6.0 pp, low confidence
MedXpertQA (Text)44.6%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)85.6%estimated ± 3.4 pp, medium confidence
React Native Evals75.4%estimated ± 2.7 pp, medium confidence
ResearchClawBench18.0%estimated ± 1.3 pp, high confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
PostTrainBench17.2%estimated ± 3.7 pp, medium confidence
FrontierCode 1.1 Extended51.2%estimated ± 3.0 pp, low confidence
HealthBench Professional29.2%estimated ± 4.2 pp, low confidence
SimpleQA38.6%estimated ± 13.4 pp, low confidence
LiveCodeBench73.4%estimated ± 14.6 pp, low confidence
Agents' Last Exam12.7%estimated ± 11.6 pp, low confidence
OpenHarmony Bench v1.030.1%estimated ± 2.7 pp, medium confidence
LifeVal29.4%estimated ± 1.6 pp, low confidence
PinchBench88.4%estimated ± 3.6 pp, medium confidence