Atlas

Models

← All models

Gemini 2.5 Flash Preview 04-17

Google · 2025-04-17

The April 17, 2025 preview snapshot of Gemini 2.5 Flash, kept separate from the later generally available release because provider behavior and benchmark results are snapshot-specific.

Benchmark scores

BenchmarkScore
Aider Polyglot47.1
AIME 202578.0
Artificial Analysis Progress Index v1215
Capability138.6
Confabulations Leaderboard Confabulation Rate4.5
Confabulations Leaderboard Non-Response Rate29.2
Confabulations Leaderboard Weighted Score16.8
CorpFin v254.2
CorpFin v2 - Exact Pages54.8
CorpFin v2 - Max Fitting Context52.3
CorpFin v2 - Shared Max Context55.4
CyberGym4.8
Epoch Capabilities Index (ECI)140
Fiction.LiveBench - 0 tokens (relevant passages only)62.5
Fiction.LiveBench - 120K tokens53.1
Fiction.LiveBench - 16K tokens47.2
Fiction.LiveBench - 1K tokens69.4
Fiction.LiveBench - 2K tokens61.1
Fiction.LiveBench - 32K tokens44.4
Fiction.LiveBench - 400 tokens63.9
Fiction.LiveBench - 4K tokens47.2
Fiction.LiveBench - 60K tokens58.3
Fiction.LiveBench - 8K tokens44.4
ForecastBench Baseline Dataset Brier Index60.7
ForecastBench Baseline Market Brier Index59.3
ForecastBench Baseline Overall Brier Index59.9
ForecastBench Preliminary Dataset Brier Index60.6
ForecastBench Tournament Dataset Brier Index60.7
ForecastBench Tournament Market Brier Index66.7
ForecastBench Tournament Overall Brier Index63.6
Loading Atlas data…