LIVE INTELLIGENCE · part of the Xentir AI Index

Claude 3.5 Sonnet vs Gemini 1.5 Flash (Sep 2024, 24 Sep 2024)

Name: Claude 3.5 Sonnet vs Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Claude 3.5 Sonnet · Anthropic, released 2024-06-20
Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) · Google DeepMind, released 2024-09-24

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources

Claude 3.5 Sonnet leads on more of the 5 benchmarks where both are measured — Claude 3.5 Sonnet on 3, Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) on 2. The remaining 4 of 9 tracked benchmarks cannot be compared: 1 has a result for only one of the two models, 3 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Claude 3.5 Sonnet leads on 3, Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) leads on 2.

Benchmark	Claude 3.5 Sonnet	Gemini 1.5 Flash (Sep 2024, 24 Sep 2024)	Leads
Epoch Capabilities Index (ECI)	130.0	129.4	Claude 3.5 Sonnet
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.540	0.473	Claude 3.5 Sonnet
MATH Level 5	0.517	0.619	Gemini 1.5 Flash (Sep 2024, 24 Sep 2024)
OTIS Mock AIME 2024-2025	0.065	0.163	Gemini 1.5 Flash (Sep 2024, 24 Sep 2024)
FrontierMath	0.010	0.000	Claude 3.5 Sonnet
FrontierMath Tier 4	0.000	Not measured	Comparison unavailable — Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) has no published result
SimpleQA Verified	Not measured	Not measured	Not measured on both
Chess Puzzles	Not measured	Not measured	Not measured on both

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) has no published result on FrontierMath Tier 4.
3 tracked benchmarks have no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Full profiles

Claude 3.5 Sonnet → · Gemini 1.5 Flash (Sep 2024, 24 Sep 2024) → · the full AI Model Rankings table