benchgap
Other · model

Solar Open 2 benchmark scores

As of 2026-11-22, Solar Open 2 (Other) has measured scores on 12 benchmarks and estimated scores on 76 more.

BenchmarkScoreSource
AA-GPQA Diamond87.2%estimated ± 2.7 pp, high confidence
AA-HLE27.1%estimated ± 3.9 pp, high confidence
AA-SciCode43.9%estimated ± 3.8 pp, high confidence
AIME2695.7%measured
Artificial Analysis Intelligence Index18.1%estimated ± 5.6 pp, medium confidence
CritPt3.7%estimated ± 4.1 pp, medium confidence
GDPval-AA29.7%estimated ± 7.5 pp, low confidence
GPQA Diamond86.3%measured
HLE37.5%estimated ± 6.5 pp, medium confidence
IFBench80.0%measured
AA-LCR62.3%measured
LiveCodeBench v692.4%measured
AA-Omniscience Accuracy26.0%estimated ± 7.7 pp, medium confidence
SciCode43.1%estimated ± 3.6 pp, high confidence
BrowseComp49.2%estimated ± 4.8 pp, low confidence
HLE w/ tools43.2%estimated ± 6.3 pp, low confidence
IFEval94.7%estimated ± 3.6 pp, high confidence
LongBench v255.0%estimated ± 5.5 pp, medium confidence
VITA-Bench38.7%estimated ± 9.9 pp, low confidence
AA Coding Index41.0%estimated ± 5.3 pp, medium confidence
APEX-Agents16.6%measured
APEX-Agents-AA23.2%estimated ± 5.5 pp, medium confidence
DeepSearchQA81.1%estimated ± 7.3 pp, low confidence
SWE-bench Verified70.4%measured
AutomationBench18.2%estimated ± 7.4 pp, low confidence
BFCL v469.6%estimated ± 4.7 pp, low confidence
CyberGym73.6%estimated ± 9.8 pp, medium confidence
JobBench32.3%estimated ± 7.9 pp, medium confidence
SkillsBench45.9%estimated ± 9.1 pp, low confidence
SWE-bench Pro47.9%estimated ± 4.5 pp, high confidence
WideResearch70.9%estimated ± 6.7 pp, low confidence
MMLU-Pro86.2%measured
AA-IFBench80.4%estimated ± 7.4 pp, medium confidence
BBH99.5%estimated ± 2.8 pp, medium confidence
GPQA86.2%estimated ± 1.2 pp, high confidence
MMLU91.1%estimated ± 2.1 pp, medium confidence
Vals GPQA Diamond85.6%estimated ± 2.1 pp, high confidence
Vals LiveCodeBench86.1%estimated ± 3.4 pp, low confidence
Vals MMLU-Pro84.6%estimated ± 1.6 pp, high confidence
MATH-50097.7%estimated ± 3.1 pp, medium confidence
MMMLU88.3%estimated ± 1.1 pp, medium confidence
AIME 202596.9%estimated ± 1.8 pp, medium confidence
AA Tau3 Banking31.7%estimated ± 4.5 pp, low confidence
ApprenticeBench3.3%estimated ± 11.0 pp, low confidence
ARC-AGI-183.2%estimated ± 2.5 pp, medium confidence
ARC-AGI-236.7%estimated ± 9.7 pp, low confidence
FrontierCode 1.1 Main10.5%estimated ± 4.2 pp, low confidence
FrontierMath v2 (Tier 4)27.2%estimated ± 4.1 pp, medium confidence
FrontierMath v2 (Tiers 1-3)40.5%estimated ± 8.8 pp, medium confidence
OSWorld-Verified64.9%estimated ± 9.4 pp, low confidence
Terminal-Bench Hard28.3%measured
Vals SWE-bench63.2%estimated ± 6.6 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)51.2%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.5%estimated ± 4.4 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)57.6%estimated ± 2.6 pp, low confidence
AA ITBench35.5%estimated ± 4.4 pp, high confidence
DeepSWE29.8%estimated ± 12.7 pp, low confidence
DRACO66.2%estimated ± 4.0 pp, low confidence
HLE w/o tools28.8%measured
Toolathlon-Verified0.3%estimated ± 8.3 pp, low confidence
ARC-AGI-30.5%estimated ± 7.2 pp, low confidence
Vibe Code Bench0.1%estimated ± 8.4 pp, medium confidence
C-Eval91.6%estimated ± 1.3 pp, medium confidence
Claw-Eval65.3%estimated ± 6.3 pp, low confidence
DeepPlanning39.1%estimated ± 13.1 pp, low confidence
HMMT Feb 202596.0%estimated ± 1.9 pp, medium confidence
HMMT Feb 202693.9%measured
HMMT Nov 202596.0%estimated ± 2.8 pp, medium confidence
MCP Atlas58.2%measured
MCP-Tasks76.3%estimated ± 0.6 pp, low confidence
MMAnswerBench84.0%estimated ± 1.3 pp, high confidence
MMLU-Redux93.8%estimated ± 0.6 pp, high confidence
NL2Repo48.3%estimated ± 3.4 pp, high confidence
QwenClawBench55.4%estimated ± 2.6 pp, high confidence
SuperGPQA70.2%estimated ± 12.4 pp, low confidence
Terminal-Bench 2.059.3%estimated ± 5.4 pp, low confidence
Toolathlon40.3%estimated ± 7.5 pp, medium confidence
MedXpertQA (Text)44.4%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)85.6%estimated ± 3.4 pp, medium confidence
React Native Evals75.3%estimated ± 2.7 pp, medium confidence
ResearchClawBench17.1%estimated ± 1.8 pp, high confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
HealthBench Professional38.8%estimated ± 4.2 pp, low confidence
SimpleQA41.6%estimated ± 11.7 pp, low confidence
LiveCodeBench73.2%estimated ± 14.6 pp, low confidence
IMOAnswerBench85.3%estimated ± 5.6 pp, medium confidence
MRCRv232.6%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.5%estimated ± 2.6 pp, low confidence