benchgap
Google · model

Gemini 1.0 Pro benchmark scores

As of 2026-11-22, Gemini 1.0 Pro (Google) has measured scores on 3 benchmarks and estimated scores on 24 more.

BenchmarkScoreSource
AA-GPQA Diamond27.7%measured
AA-HLE4.2%measured
Artificial Analysis Intelligence Index5.3%measured
CritPt0.2%estimated ± 3.4 pp, high confidence
GPQA Diamond68.8%estimated ± 2.4 pp, medium confidence
HLE16.7%estimated ± 8.5 pp, low confidence
AA-Omniscience Accuracy16.1%estimated ± 7.3 pp, medium confidence
BioMysteryBench (human-difficult)26.3%estimated ± 8.3 pp, low confidence
MMLU-Pro74.7%estimated ± 5.4 pp, medium confidence
GPQA34.1%estimated ± 6.1 pp, medium confidence
MMLU82.8%estimated ± 3.8 pp, high confidence
Vals GPQA Diamond26.9%estimated ± 3.2 pp, medium confidence
Vals MMLU-Pro49.7%estimated ± 3.0 pp, medium confidence
MMMLU62.7%estimated ± 1.7 pp, medium confidence
AA MMLU-Pro82.7%estimated ± 1.2 pp, medium confidence
ARC-AGI-171.0%estimated ± 7.9 pp, low confidence
ARC-AGI-226.1%estimated ± 14.4 pp, low confidence
HLE w/o tools20.1%estimated ± 4.9 pp, high confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
C-Eval87.2%estimated ± 1.0 pp, low confidence
MMLU-Redux84.7%estimated ± 1.2 pp, low confidence
SuperGPQA61.7%estimated ± 10.1 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
SimpleQA2.2%estimated ± 7.8 pp, low confidence
BioBasicsBench6.9%estimated ± 10.2 pp, low confidence