benchgap
Other · model

Inkling-Small benchmark scores

As of 2026-11-21, Inkling-Small (Other) has measured scores on 41 benchmarks and estimated scores on 152 more.

BenchmarkScoreSource
AA-GPQA Diamond89.5%measured
AA-HLE33.3%measured
AA-SciCode49.7%measured
AIME2695.5%measured
Artificial Analysis Intelligence Index12.9%measured
CritPt8.3%measured
GDPval-AA31.2%measured
GPQA Diamond89.5%measured
HLE47.8%measured
IFBench82.2%measured
AA-LCR75.7%measured
LiveCodeBench v689.1%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy31.8%measured
SciCode48.7%measured
Terminal-Bench 2.164.7%measured
BrowseComp77.4%measured
HLE w/ tools48.9%estimated ± 5.3 pp, medium confidence
IFEval95.0%estimated ± 3.6 pp, high confidence
LongBench v262.2%estimated ± 5.5 pp, medium confidence
VITA-Bench43.9%estimated ± 6.7 pp, low confidence
τ²-bench results92.9%estimated ± 11.8 pp, low confidence
AA Coding Index52.9%measured
AA-MMMU-Pro74.0%measured
APEX-Agents23.5%estimated ± 9.4 pp, low confidence
APEX-Agents-AA23.5%estimated ± 4.4 pp, high confidence
BioMysteryBench (human-difficult)42.3%estimated ± 6.8 pp, low confidence
DeepSearchQA87.1%estimated ± 4.5 pp, high confidence
SWE-bench Verified80.2%measured
BFCL v474.6%estimated ± 2.7 pp, high confidence
CyberGym64.7%estimated ± 5.3 pp, low confidence
JobBench52.0%estimated ± 7.9 pp, medium confidence
SkillsBench48.7%estimated ± 4.1 pp, medium confidence
SWE-bench Pro55.9%measured
WideResearch76.5%estimated ± 3.5 pp, high confidence
AA Agentic Index25.0%measured
MMLU-Pro85.3%estimated ± 2.5 pp, medium confidence
AA-IFBench80.4%estimated ± 7.4 pp, low confidence
FailureSensorIQ63.5%estimated ± 5.0 pp, medium confidence
GPQA89.5%measured
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond83.6%measured
Vals LiveCodeBench85.9%measured
Vals MMLU-Pro85.6%measured
MATH-50097.7%estimated ± 3.1 pp, medium confidence
MMMLU89.2%estimated ± 0.7 pp, medium confidence
MMMU82.4%estimated ± 0.8 pp, high confidence
Chess Puzzles28.3%estimated ± 4.7 pp, medium confidence
AIME 202596.8%estimated ± 1.8 pp, medium confidence
AA MMLU-Pro86.1%estimated ± 0.7 pp, high confidence
Gert Labs59.4%estimated ± 7.1 pp, medium confidence
AA-AnalystAgent46.5%estimated ± 3.7 pp, medium confidence
AA EnterpriseOps-Gym42.7%measured
AA Harvey LAB v1.083.8%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking33.8%estimated ± 3.6 pp, medium confidence
AA Terminal-Bench 2.180.1%estimated ± 2.5 pp, medium confidence
ApprenticeBench18.9%estimated ± 11.0 pp, low confidence
ARC-AGI-184.0%measured
ARC-AGI-240.1%measured
CursorBench 3.143.3%estimated ± 3.4 pp, low confidence
CursorBench 3.252.0%estimated ± 3.6 pp, high confidence
EBR-bench0.0%estimated ± 10.4 pp, low confidence
Terminal-Bench 3.07.7%estimated ± 3.2 pp, medium confidence
FrontierCode 1.1 Main27.9%estimated ± 4.2 pp, medium confidence
FrontierMath v2 (Tier 4)17.1%measured
FrontierMath v2 (Tiers 1-3)46.3%measured
FrontierSWE v28.5%estimated ± 8.3 pp, medium confidence
Furniture Assembly32.9%estimated ± 9.3 pp, low confidence
MaxxBench41.7%estimated ± 5.7 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
Mystery Game Puzzles6.0%measured
NYT Connections58.3%estimated ± 13.8 pp, low confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified69.7%estimated ± 5.7 pp, medium confidence
ParseBench-161.6%estimated ± 1.0 pp, medium confidence
Terminal-Bench 4.10.9%measured
Terminal-Bench Hard52.7%estimated ± 2.8 pp, low confidence
Vals SWE-bench82.2%measured
Terminal-Bench 2.1 (Vals AI)55.1%measured
VulcanBench v384.2%estimated ± 5.6 pp, low confidence
CWE-Bench-AA49.4%estimated ± 6.4 pp, medium confidence
AA Cyber Index16.4%estimated ± 9.2 pp, low confidence
DeepsecBench-AA4.3%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.7%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)51.8%estimated ± 0.8 pp, low confidence
AA ITBench40.8%estimated ± 4.0 pp, high confidence
Bug Hunt Bench22.1%estimated ± 10.5 pp, low confidence
Chartography (tools)79.6%estimated ± 4.1 pp, low confidence
CursorBench 4.032.5%estimated ± 3.3 pp, medium confidence
CWE-bench v140.6%estimated ± 6.4 pp, medium confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
DRACO76.7%estimated ± 2.0 pp, medium confidence
FrontierCode 2.020.0%estimated ± 6.7 pp, low confidence
FrontierPhysics1.1%estimated ± 4.7 pp, medium confidence
HLE w/o tools31.6%measured
OSWorld 2.146.9%estimated ± 6.0 pp, low confidence
OSWorld 2.1 Offline8.5%estimated ± 1.9 pp, low confidence
PostTrainBench v1.126.0%estimated ± 3.7 pp, high confidence
SpireClimb0.0%estimated ± 9.3 pp, low confidence
StealthMark27.5%measured
Terminal-Bench 4.010.0%estimated ± 4.5 pp, medium confidence
Toolathlon-Verified54.4%measured
VulcanBench Frontier v479.9%estimated ± 6.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
AA Terminal-Bench 4.00.5%estimated ± 6.2 pp, low confidence
ARC-AGI-30.8%estimated ± 7.2 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
MKA25.8%estimated ± 6.4 pp, low confidence
SkillsBench official leaderboard (BenchFlow)44.0%estimated ± 6.3 pp, low confidence
CompileBench53.4%estimated ± 10.0 pp, low confidence
Vibe Code Bench49.2%estimated ± 8.4 pp, medium confidence
FACTS Multimodal39.5%estimated ± 4.7 pp, high confidence
Hermes Bench60.7%estimated ± 2.9 pp, high confidence
Hermes Index27.8%estimated ± 8.7 pp, medium confidence
ParseBench-263.5%estimated ± 5.0 pp, medium confidence
CharXiv81.3%measured
CharXiv w/o tools77.4%measured
ExploitBench12.6%estimated ± 7.2 pp, low confidence
ExploitGym0.0%estimated ± 9.2 pp, low confidence
AI2D_TEST93.4%estimated ± 0.9 pp, medium confidence
C-Eval89.4%estimated ± 1.0 pp, medium confidence
Claw-Eval71.6%estimated ± 6.3 pp, low confidence
CountBench94.3%estimated ± 2.9 pp, medium confidence
DeepPlanning49.9%estimated ± 13.1 pp, low confidence
DynaMath86.1%estimated ± 0.8 pp, medium confidence
ERQA58.6%estimated ± 2.9 pp, medium confidence
HMMT Feb 202596.9%estimated ± 1.8 pp, low confidence
HMMT Feb 202690.2%measured
HMMT Nov 202594.1%estimated ± 1.5 pp, medium confidence
MathVision82.9%estimated ± 3.0 pp, high confidence
MCP Atlas79.6%measured
MLVU (M-Avg)86.1%estimated ± 1.5 pp, high confidence
MMAnswerBench83.6%estimated ± 1.3 pp, high confidence
MMLU-Redux95.0%estimated ± 0.8 pp, medium confidence
MMMU-Pro74.0%measured
NL2Repo47.1%estimated ± 4.7 pp, high confidence
PostTrainBench v127.1%estimated ± 3.6 pp, high confidence
QwenClawBench65.6%estimated ± 2.6 pp, medium confidence
RealWorldQA84.0%estimated ± 1.5 pp, high confidence
ScreenSpot Pro73.7%estimated ± 6.8 pp, medium confidence
SimpleVQA61.6%estimated ± 7.5 pp, medium confidence
SuperGPQA87.2%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.062.6%estimated ± 5.8 pp, medium confidence
Toolathlon46.9%estimated ± 4.2 pp, high confidence
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)82.3%estimated ± 1.3 pp, high confidence
Video-MME (with subtitle)87.1%estimated ± 2.9 pp, high confidence
VideoMMMU85.5%estimated ± 1.5 pp, medium confidence
We-Math80.5%estimated ± 7.4 pp, low confidence
AA LiveCodeBench92.9%estimated ± 2.6 pp, medium confidence
HealthBench Hard0.8%estimated ± 5.1 pp, low confidence
LiveCodeBench Pro80.5%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)60.8%estimated ± 2.4 pp, high confidence
MedXpertQA (Text)52.3%estimated ± 4.5 pp, medium confidence
MMLU-Pro (Arcee)86.7%estimated ± 3.4 pp, low confidence
React Native Evals79.7%estimated ± 2.7 pp, medium confidence
ResearchClawBench19.3%estimated ± 1.8 pp, high confidence
SWE-Rebench61.8%estimated ± 3.6 pp, medium confidence
PostTrainBench23.7%estimated ± 3.7 pp, high confidence
DAYJOB0.0%estimated ± 3.2 pp, medium confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, medium confidence
BioMysteryBench (human-solvable)82.3%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended54.6%estimated ± 3.0 pp, low confidence
HealthBench (raw)42.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)52.7%estimated ± 2.5 pp, low confidence
HealthBench Professional41.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)53.3%estimated ± 4.5 pp, medium confidence
HLE-Verified16.4%estimated ± 2.0 pp, low confidence
LABBench280.7%estimated ± 1.8 pp, low confidence
ScarfBench24.8%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.0%estimated ± 2.8 pp, low confidence
Cookie-Bench76.9%estimated ± 1.3 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA34.3%estimated ± 4.3 pp, low confidence
LiveCodeBench79.4%estimated ± 14.6 pp, low confidence
Agents' Last Exam24.9%estimated ± 11.6 pp, low confidence
BabyVision w/ Python85.3%estimated ± 3.7 pp, low confidence
OpenHarmony Bench v1.053.1%estimated ± 2.4 pp, high confidence
SEC-Bench Pro30.8%estimated ± 9.3 pp, low confidence
IMOAnswerBench83.3%estimated ± 5.6 pp, medium confidence
BabyVision43.1%estimated ± 7.4 pp, low confidence
MMVU74.7%estimated ± 2.7 pp, medium confidence
PerceptionBench55.3%estimated ± 3.8 pp, low confidence
ZeroBench15.1%estimated ± 7.1 pp, low confidence
MRCRv284.6%estimated ± 11.3 pp, low confidence
LVBench63.7%estimated ± 8.2 pp, low confidence
MMLongBench-Doc61.2%estimated ± 2.6 pp, low confidence
OCRBench V270.0%estimated ± 3.3 pp, high confidence
BioBasicsBench20.5%estimated ± 2.2 pp, low confidence
LifeVal68.5%estimated ± 1.6 pp, medium confidence
MMMU-Pro w/ Python77.3%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.0%estimated ± 5.2 pp, low confidence
PinchBench90.1%estimated ± 3.6 pp, medium confidence