BenchAtlas

Rankings / Google

Gemini 3.1 Flash Lite

released 2026-03-03

BenchAtlas Index

as of 2026-09-11
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

10 results
external indices
ECIlow effort144.5 pointsindependentEpoch AI Benchmarking Hub
ECIhigh effort144.5 pointsindependentEpoch AI Benchmarking Hub
ECIminimal effort144.5 pointsindependentEpoch AI Benchmarking Hub
ECI144.5 pointsindependentEpoch AI Benchmarking Hub
knowledge science
GPQA Diamondhigh effort81.8 %independentEpoch AI Benchmarking Hub
2026-08-06
GPQA Diamondlow effort74.2 %independentEpoch AI Benchmarking Hub
2026-08-06
GPQA Diamondminimal effort73.7 %independentEpoch AI Benchmarking Hub
2026-08-06
reasoning math
OTIS Mock AIME 2024–2025high effort80.0 %independentEpoch AI Benchmarking Hub
2026-08-06
OTIS Mock AIME 2024–2025low effort44.4 %independentEpoch AI Benchmarking Hub
2026-08-06
OTIS Mock AIME 2024–2025minimal effort37.8 %independentEpoch AI Benchmarking Hub
2026-08-06