Rankings / Google DeepMind

Gemini 2.0 Pro Exp 02.05

released 2025-02-05

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

5 results

external indices

ECI

135.6 points

independent

Epoch AI Benchmarking Hub

knowledge science

GPQA Diamond

65.7 %

independent

Epoch AI Benchmarking Hub

2025-02-07

professional

CorpFin		43.4 %	independent	Vals AI
TaxEval		68.2 %	independent	Vals AI

reasoning math

MATH Level 5

83.5 %

independent

Epoch AI Benchmarking Hub

2025-02-06