BenchAtlas

Rankings / Google DeepMind

Gemini 2.5 Flash Preview 05.20

released 2025-05-20

BenchAtlas Index

as of 2026-07-14
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

46 results
external indices
ECI142.2 pointsindependentEpoch AI Benchmarking Hub
ECI16K budget142.2 pointsindependentEpoch AI Benchmarking Hub
ECI8K budget142.2 pointsindependentEpoch AI Benchmarking Hub
ECI1K budget142.2 pointsindependentEpoch AI Benchmarking Hub
ECI23K budget142.2 pointsindependentEpoch AI Benchmarking Hub
reasoning math
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 24K budget39.1 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
36.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 16K budget36.0 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 8K budget34.5 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
33.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 16K budget33.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 24K budget32.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 8K budget25.8 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 1K budget18.0 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 1K budget16.0 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 24K budget2.6 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 24K budget2.5 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 1K budget2.2 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 8K budget2.1 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 16K budget2.0 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
1.9 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
1.7 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 16K budget1.1 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 8K budget1.1 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 24K budget0.3 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 16K budget0.3 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 24K budget0.3 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 16K budget0.3 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 16K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 8K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 8K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 24K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 24K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 16K budget0.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 8K budget0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 8K budget0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 1K budget0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 1K budget0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 1K budget0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 1K budget0.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 1K budget0.0 %independentARC Prize Leaderboard
OTIS Mock AIME 2024–202570.8 %independentEpoch AI Benchmarking Hub
2025-05-20

Related variants

Gemini 2.5 Flash Preview 04.17Gemini 2.5 Flash Preview 09 2025