benchgap
Other · model

Laguna XS 2.1 benchmark scores

As of 2026-11-22, Laguna XS 2.1 (Other) has measured scores on 5 benchmarks and estimated scores on 58 more.

BenchmarkScoreSource
AA-SciCode43.9%estimated ± 3.6 pp, high confidence
GDPval-AA13.9%estimated ± 10.5 pp, low confidence
LiveCodeBench v684.7%estimated ± 2.7 pp, high confidence
SciCode43.4%estimated ± 3.6 pp, high confidence
BrowseComp62.6%estimated ± 8.8 pp, low confidence
HLE w/ tools37.4%estimated ± 5.7 pp, low confidence
AA Coding Index42.0%estimated ± 5.3 pp, medium confidence
APEX-Agents-AA7.5%estimated ± 9.3 pp, low confidence
SWE-bench Verified70.9%measured
CyberGym35.6%estimated ± 11.0 pp, low confidence
JobBench11.8%estimated ± 14.2 pp, low confidence
SWE-bench Pro47.6%measured
WideResearch57.7%estimated ± 3.3 pp, medium confidence
AA Agentic Index10.4%estimated ± 9.4 pp, low confidence
Vals LiveCodeBench73.6%estimated ± 4.7 pp, medium confidence
Gert Labs17.0%measured
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
CursorBench 3.145.9%estimated ± 5.6 pp, low confidence
CursorBench 3.234.7%estimated ± 3.6 pp, medium confidence
FrontierCode 1.1 Main11.4%estimated ± 4.2 pp, low confidence
FrontierSWE v20.0%estimated ± 8.3 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, medium confidence
OSWorld-Verified59.4%estimated ± 8.6 pp, low confidence
Terminal-Bench Hard41.3%estimated ± 4.0 pp, medium confidence
Vals SWE-bench63.9%estimated ± 6.6 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)32.3%estimated ± 6.4 pp, medium confidence
CWE-Bench-AA27.8%estimated ± 8.1 pp, low confidence
AA Cyber Index1.3%estimated ± 12.4 pp, low confidence
DeepsecBench-AA4.8%estimated ± 8.2 pp, low confidence
AA ITBench35.5%estimated ± 4.6 pp, low confidence
Bug Hunt Bench25.6%estimated ± 12.1 pp, low confidence
CursorBench 4.026.2%estimated ± 3.3 pp, medium confidence
CWE-bench v130.9%estimated ± 5.7 pp, low confidence
DeepSWE44.1%estimated ± 11.2 pp, low confidence
FrontierCode 2.018.7%estimated ± 6.7 pp, low confidence
OSWorld 2.10.4%estimated ± 3.6 pp, medium confidence
PostTrainBench v1.118.7%estimated ± 4.4 pp, medium confidence
SWE Multilingual63.1%measured
Toolathlon-Verified50.8%estimated ± 3.0 pp, medium confidence
VulcanBench Frontier v471.8%estimated ± 8.3 pp, low confidence
AA AutomationBench36.1%estimated ± 9.9 pp, low confidence
GDP.pdf8.3%estimated ± 4.2 pp, medium confidence
CWE-bench23.1%estimated ± 6.2 pp, low confidence
MKA32.7%estimated ± 4.6 pp, medium confidence
Vibe Code Bench0.1%estimated ± 8.4 pp, medium confidence
Hermes Index12.5%estimated ± 5.7 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
INCLUDE81.7%estimated ± 2.0 pp, low confidence
MMLU-ProX81.9%estimated ± 1.3 pp, medium confidence
NL2Repo31.8%estimated ± 6.1 pp, medium confidence
PostTrainBench v112.3%estimated ± 4.6 pp, medium confidence
Terminal-Bench 2.037.5%measured
Toolathlon37.8%estimated ± 8.0 pp, low confidence
LiveCodeBench Pro73.2%estimated ± 6.0 pp, low confidence
React Native Evals75.5%estimated ± 2.7 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
PostTrainBench17.3%estimated ± 3.7 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
FrontierCode 1.1 Extended51.3%estimated ± 3.0 pp, low confidence
LiveCodeBench73.6%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
OpenHarmony Bench v1.053.3%estimated ± 4.9 pp, low confidence
LifeVal0.2%estimated ± 5.0 pp, low confidence