benchgap
Other · model

A.X K2 benchmark scores

As of 2026-11-22, A.X K2 (Other) has measured scores on 15 benchmarks and estimated scores on 92 more.

BenchmarkScoreSource
AA-GPQA Diamond85.7%measured
AA-HLE29.6%measured
AA-SciCode41.0%measured
AIME2697.1%measured
Artificial Analysis Intelligence Index9.0%measured
CritPt8.9%measured
GDPval-AA23.0%measured
GPQA Diamond85.6%measured
HLE27.8%measured
IFBench75.9%measured
AA-LCR66.0%measured
LiveCodeBench v684.0%measured
AA-Omniscience Accuracy17.5%measured
SciCode41.0%measured
Terminal-Bench 2.136.0%measured
BrowseComp65.9%estimated ± 9.2 pp, medium confidence
HLE w/ tools44.9%estimated ± 5.3 pp, low confidence
IFEval94.0%estimated ± 3.6 pp, high confidence
LongBench v256.5%estimated ± 5.5 pp, medium confidence
AA Coding Index49.7%estimated ± 5.7 pp, medium confidence
APEX-Agents16.4%estimated ± 9.4 pp, low confidence
APEX-Agents-AA20.3%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)42.9%estimated ± 6.8 pp, low confidence
DeepSearchQA82.8%estimated ± 9.6 pp, medium confidence
SWE-bench Verified69.5%estimated ± 5.6 pp, medium confidence
BFCL v472.9%estimated ± 2.7 pp, high confidence
CyberGym49.3%estimated ± 6.0 pp, low confidence
JobBench19.7%estimated ± 8.7 pp, medium confidence
SWE-bench Pro47.1%estimated ± 6.0 pp, medium confidence
WideResearch73.1%estimated ± 7.8 pp, low confidence
AA Agentic Index17.4%estimated ± 3.1 pp, high confidence
MMLU-Pro81.9%estimated ± 5.0 pp, medium confidence
AA-IFBench75.5%estimated ± 7.4 pp, medium confidence
GPQA85.5%estimated ± 1.2 pp, high confidence
MMLU80.7%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond84.9%estimated ± 2.1 pp, high confidence
Vals LiveCodeBench84.1%estimated ± 0.8 pp, low confidence
Vals MMLU-Pro84.2%estimated ± 1.6 pp, high confidence
MATH-50097.9%estimated ± 3.1 pp, low confidence
MMMLU89.3%estimated ± 0.7 pp, medium confidence
AIME 202598.2%estimated ± 1.8 pp, low confidence
AA MMLU-Pro83.7%estimated ± 0.8 pp, medium confidence
Gert Labs30.8%estimated ± 10.0 pp, low confidence
AA Tau3 Banking28.4%estimated ± 4.1 pp, high confidence
ARC-AGI-181.9%estimated ± 2.5 pp, medium confidence
ARC-AGI-232.9%estimated ± 9.7 pp, low confidence
CursorBench 3.239.3%estimated ± 5.3 pp, low confidence
FrontierCode 1.1 Main0.0%estimated ± 6.6 pp, low confidence
FrontierMath v2 (Tiers 1-3)47.8%estimated ± 8.8 pp, medium confidence
FrontierSWE v26.3%estimated ± 14.2 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified67.6%estimated ± 8.4 pp, low confidence
Terminal-Bench 4.10.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench65.5%estimated ± 5.3 pp, low confidence
Terminal-Bench 2.1 (Vals AI)34.3%estimated ± 7.3 pp, low confidence
CWE-Bench-AA30.5%estimated ± 10.1 pp, low confidence
DeepsecBench-AA0.8%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)48.5%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)53.0%estimated ± 0.8 pp, low confidence
AA ITBench36.7%estimated ± 5.1 pp, low confidence
Bug Hunt Bench15.2%estimated ± 10.5 pp, low confidence
CursorBench 4.027.5%estimated ± 4.9 pp, medium confidence
CWE-bench v132.3%estimated ± 6.4 pp, low confidence
DeepSWE34.8%estimated ± 7.5 pp, low confidence
DRACO70.8%estimated ± 2.0 pp, medium confidence
FrontierCode 2.026.1%estimated ± 9.3 pp, low confidence
HLE w/o tools26.5%estimated ± 2.7 pp, medium confidence
PostTrainBench v1.125.7%estimated ± 7.4 pp, low confidence
Toolathlon-Verified48.7%estimated ± 3.1 pp, medium confidence
VulcanBench Frontier v470.9%estimated ± 6.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Hermes Bench53.8%estimated ± 2.9 pp, high confidence
Hermes Index21.3%estimated ± 8.7 pp, medium confidence
ExploitGym0.5%estimated ± 10.6 pp, low confidence
C-Eval92.6%estimated ± 0.9 pp, medium confidence
HMMT Feb 202597.6%estimated ± 1.9 pp, low confidence
HMMT Feb 202691.6%estimated ± 4.0 pp, high confidence
HMMT Nov 202595.1%estimated ± 3.2 pp, high confidence
MCP Atlas60.8%estimated ± 10.7 pp, low confidence
MMAnswerBench86.5%estimated ± 1.3 pp, high confidence
MMLU-Redux93.2%estimated ± 0.8 pp, low confidence
NL2Repo34.8%estimated ± 3.4 pp, high confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
SuperGPQA68.4%estimated ± 7.2 pp, medium confidence
Toolathlon35.3%estimated ± 6.3 pp, medium confidence
HealthBench Hard28.2%estimated ± 8.6 pp, low confidence
MedXpertQA (Text)42.9%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)85.3%estimated ± 3.4 pp, medium confidence
React Native Evals72.8%estimated ± 4.7 pp, medium confidence
ResearchClawBench15.5%estimated ± 2.2 pp, medium confidence
BioMysteryBench (human-solvable)82.6%estimated ± 0.6 pp, low confidence
HealthBench (raw)38.5%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)49.6%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)49.7%estimated ± 4.5 pp, medium confidence
HLE-Verified0.0%estimated ± 6.8 pp, low confidence
LABBench275.4%estimated ± 2.4 pp, low confidence
ScarfBench39.1%estimated ± 14.0 pp, low confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA14.7%estimated ± 4.3 pp, medium confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
IMOAnswerBench75.1%estimated ± 10.7 pp, low confidence
MRCRv251.6%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.7%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence