benchgap
Other · model

Laguna XS.2 benchmark scores

As of 2026-11-22, Laguna XS.2 (Other) has measured scores on 9 benchmarks and estimated scores on 42 more.

BenchmarkScoreSource
AA-GPQA Diamond59.7%estimated ± 3.6 pp, high confidence
AA-HLE4.8%estimated ± 6.2 pp, medium confidence
AA-SciCode43.2%estimated ± 3.6 pp, high confidence
Artificial Analysis Intelligence Index6.4%estimated ± 5.8 pp, medium confidence
CritPt0.8%estimated ± 5.3 pp, medium confidence
HLE16.5%estimated ± 9.2 pp, low confidence
LiveCodeBench v680.6%estimated ± 2.2 pp, low confidence
AA-Omniscience Accuracy13.6%estimated ± 6.5 pp, medium confidence
SciCode42.9%estimated ± 3.6 pp, high confidence
Terminal-Bench 2.13.7%estimated ± 6.7 pp, low confidence
AA Coding Index40.1%estimated ± 5.3 pp, medium confidence
SWE-bench Verified69.9%measured
SWE-bench Pro46.3%measured
MMLU-Pro74.9%estimated ± 4.8 pp, high confidence
GPQA59.4%estimated ± 4.5 pp, high confidence
MMLU83.0%estimated ± 1.2 pp, high confidence
Vals GPQA Diamond55.1%measured
Vals LiveCodeBench67.8%measured
Vals MMLU-Pro69.1%measured
ARC-AGI-130.0%estimated ± 8.4 pp, low confidence
CursorBench 3.145.0%estimated ± 5.6 pp, low confidence
CursorBench 3.231.6%estimated ± 3.6 pp, medium confidence
FrontierCode 1.1 Main9.7%estimated ± 4.2 pp, low confidence
FrontierSWE v20.0%estimated ± 8.3 pp, low confidence
Terminal-Bench 4.12.7%estimated ± 14.9 pp, low confidence
Terminal-Bench Hard43.3%estimated ± 3.9 pp, medium confidence
Vals SWE-bench55.2%measured
Terminal-Bench 2.1 (Vals AI)25.8%measured
VulcanBench v377.6%estimated ± 5.6 pp, low confidence
Bug Hunt Bench25.0%estimated ± 12.1 pp, low confidence
CursorBench 4.025.2%estimated ± 3.3 pp, medium confidence
DeepSWE43.1%estimated ± 11.2 pp, low confidence
FrontierCode 2.018.6%estimated ± 6.7 pp, low confidence
HLE w/o tools24.3%estimated ± 4.9 pp, medium confidence
PostTrainBench v1.118.0%estimated ± 4.4 pp, medium confidence
SWE Multilingual57.7%measured
VulcanBench Frontier v470.9%estimated ± 8.3 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, medium confidence
INCLUDE80.2%estimated ± 2.0 pp, low confidence
MMLU-ProX81.2%estimated ± 1.3 pp, medium confidence
NL2Repo36.4%estimated ± 4.7 pp, medium confidence
PostTrainBench v111.0%estimated ± 4.6 pp, medium confidence
Terminal-Bench 2.035.7%measured
AA LiveCodeBench82.6%estimated ± 2.6 pp, high confidence
LiveCodeBench Pro71.9%estimated ± 6.0 pp, low confidence
React Native Evals75.1%estimated ± 2.7 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
PostTrainBench16.6%estimated ± 3.7 pp, medium confidence
FrontierCode 1.1 Extended50.7%estimated ± 3.0 pp, low confidence
LiveCodeBench72.9%estimated ± 14.6 pp, low confidence
OpenHarmony Bench v1.046.5%estimated ± 3.2 pp, medium confidence