benchgap
OpenAI · model

GPT-OSS 120B benchmark scores

As of 2026-11-22, GPT-OSS 120B (OpenAI) has measured scores on 25 benchmarks and estimated scores on 105 more.

BenchmarkScoreSource
AA-GPQA Diamond78.2%measured
AA-HLE19.6%measured
AA-SciCode34.0%measured
AIME2691.6%estimated ± 4.3 pp, medium confidence
Artificial Analysis Intelligence Index3.8%measured
CritPt1.1%measured
GDPval-AA5.4%measured
GPQA Diamond80.2%estimated ± 1.2 pp, high confidence
HLE14.9%measured
IFBench67.0%estimated ± 6.6 pp, medium confidence
AA-LCR52.0%measured
LiveCodeBench v678.5%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy21.7%measured
SciCode34.3%estimated ± 3.1 pp, high confidence
BrowseComp29.5%estimated ± 4.2 pp, medium confidence
HLE w/ tools26.8%estimated ± 4.1 pp, low confidence
IFEval92.8%estimated ± 2.8 pp, high confidence
LongBench v252.5%estimated ± 5.5 pp, medium confidence
τ²-bench results65.8%measured
AA Coding Index30.4%measured
APEX-Agents3.5%estimated ± 9.4 pp, low confidence
APEX-Agents-AA3.1%measured
BioMysteryBench (human-difficult)18.0%estimated ± 6.8 pp, low confidence
DeepSearchQA62.0%estimated ± 4.5 pp, medium confidence
SWE-bench Verified62.4%measured
BFCL v463.5%estimated ± 2.7 pp, high confidence
CyberGym50.3%estimated ± 5.3 pp, low confidence
JobBench0.0%estimated ± 8.2 pp, low confidence
SWE-bench Pro39.0%estimated ± 4.5 pp, high confidence
WideResearch63.1%estimated ± 3.3 pp, medium confidence
AA Agentic Index6.2%measured
MMLU-Pro81.9%estimated ± 4.0 pp, high confidence
AA-IFBench69.0%measured
AIME 202495.8%measured
BBH95.6%estimated ± 2.4 pp, low confidence
FailureSensorIQ50.5%measured
GPQA80.1%measured
MMLU90.0%measured
Vals GPQA Diamond77.3%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench71.5%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro83.1%estimated ± 2.3 pp, high confidence
MATH-50098.2%estimated ± 1.2 pp, medium confidence
MMMLU86.5%estimated ± 0.7 pp, medium confidence
Chess Puzzles25.0%estimated ± 4.7 pp, medium confidence
AIME 202592.5%measured
AA MMLU-Pro84.3%estimated ± 0.8 pp, medium confidence
Gert Labs21.1%measured
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking19.6%estimated ± 3.7 pp, medium confidence
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
ARC-AGI-151.6%estimated ± 6.7 pp, low confidence
ARC-AGI-20.0%estimated ± 10.9 pp, low confidence
CursorBench 3.228.1%estimated ± 5.3 pp, low confidence
EBR-bench0.0%estimated ± 10.4 pp, low confidence
FrontierSWE v22.1%estimated ± 14.2 pp, low confidence
Furniture Assembly32.9%estimated ± 9.3 pp, low confidence
MaxxBench47.2%estimated ± 8.8 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, medium confidence
Mystery Game Puzzles0.0%measured
NYT Connections58.3%estimated ± 13.8 pp, low confidence
OSWorld-Verified58.3%estimated ± 8.4 pp, low confidence
Vals SWE-bench54.3%estimated ± 5.5 pp, medium confidence
CWE-Bench-AA32.3%estimated ± 8.1 pp, low confidence
AA Cyber Index4.5%estimated ± 9.2 pp, low confidence
DeepsecBench-AA6.2%estimated ± 8.2 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)4.7%estimated ± 2.1 pp, low confidence
AA ITBench34.8%estimated ± 4.0 pp, medium confidence
Bug Hunt Bench11.2%estimated ± 10.5 pp, low confidence
CWE-bench v133.7%estimated ± 5.7 pp, low confidence
DeepSWE15.9%estimated ± 7.5 pp, low confidence
DRACO36.3%estimated ± 2.0 pp, low confidence
FrontierPhysics2.5%estimated ± 5.0 pp, low confidence
HLE w/o tools18.9%estimated ± 4.9 pp, medium confidence
OSWorld 2.11.6%estimated ± 3.6 pp, medium confidence
SpireClimb0.0%estimated ± 9.3 pp, low confidence
StealthMark28.4%estimated ± 9.2 pp, low confidence
Toolathlon-Verified20.9%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v462.6%estimated ± 6.8 pp, low confidence
AA AutomationBench38.4%estimated ± 9.9 pp, low confidence
GDP.pdf10.0%estimated ± 4.2 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
CWE-bench26.5%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)41.4%estimated ± 6.3 pp, low confidence
CompileBench42.2%measured
Vibe Code Bench27.7%estimated ± 6.5 pp, low confidence
FACTS Multimodal37.5%estimated ± 5.8 pp, low confidence
Hermes Bench22.4%estimated ± 2.9 pp, medium confidence
Hermes Index15.0%estimated ± 5.7 pp, low confidence
ExploitBench0.0%estimated ± 7.2 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
C-Eval86.0%estimated ± 0.9 pp, low confidence
HMMT Feb 202595.5%estimated ± 2.9 pp, high confidence
HMMT Feb 202678.0%estimated ± 11.0 pp, low confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MMLU-Redux93.7%estimated ± 0.8 pp, medium confidence
NL2Repo19.9%estimated ± 4.7 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
SuperGPQA56.3%estimated ± 7.2 pp, medium confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
AA LiveCodeBench87.8%measured
HealthBench Hard10.4%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)81.3%estimated ± 4.0 pp, medium confidence
React Native Evals71.6%measured
ResearchClawBench9.0%estimated ± 1.9 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
DAYJOB1.3%estimated ± 3.2 pp, medium confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)27.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)45.8%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)39.3%estimated ± 4.5 pp, medium confidence
HLE-Verified16.9%estimated ± 7.1 pp, low confidence
ScarfBench24.4%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
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA20.4%estimated ± 4.3 pp, medium confidence
LiveCodeBench67.7%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
SEC-Bench Pro29.0%estimated ± 9.3 pp, low confidence
MRCRv223.0%estimated ± 11.3 pp, low confidence
MMLongBench-Doc59.6%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
LifeVal0.9%estimated ± 5.0 pp, low confidence
ExploitBench Internal Port0.0%estimated ± 5.2 pp, low confidence