Compare AI models

Specifications
Context window
1M1M
API pricing
Input price
$0.75$1.25
Output price
$3.75$4.25
Cached input price
$0.075$0.15
Cheapest input
$0.375Google AI Studio$1.25Google
Cheapest output
$1.875Google AI Studio$4.25Google
$338Google list price$463Meta list price
Benchmarks
CheatBench
75.2%39%
CursorBench 4.0
39.6%41.6%
DeepSWE 1.1
73.7%75.4%
Terminal-Bench 4.0
19.1%14.55%
Terminal-Bench 2.1
89.4%88.8%
OSWorld 2.0
59%66.9%
GDPval-AA v2
15451754
threejseval
15641442
Overview
CompanyGoogleMeta
Release dateSep 2 2026Sep 2 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Muse Spark 1.3 leads Gemini 3.8 Flash on 5 of the 8 benchmarks they both report. Gemini 3.8 Flash is cheaper on both input and output: $0.75 vs $1.25 per million input tokens, and $3.75 vs $4.25 per million output tokens. Both models were released on the same day — Sep 2 2026.

Context windows are 1M (Gemini 3.8 Flash) vs 1M (Muse Spark 1.3).

On CheatBench, Muse Spark 1.3 leads at 39% vs Gemini 3.8 Flash at 75.2%. On CursorBench 4.0, Muse Spark 1.3 leads at 41.6% vs Gemini 3.8 Flash at 39.6%. On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs Gemini 3.8 Flash at 73.7%. On Terminal-Bench 4.0, Gemini 3.8 Flash leads at 19.1% vs Muse Spark 1.3 at 14.55%. On Terminal-Bench 2.1, Gemini 3.8 Flash leads at 89.4% vs Muse Spark 1.3 at 88.8%. On OSWorld 2.0, Muse Spark 1.3 leads at 66.9% vs Gemini 3.8 Flash at 59%. On GDPval-AA v2, Muse Spark 1.3 leads at 1754 vs Gemini 3.8 Flash at 1545. On threejseval, Gemini 3.8 Flash leads at 1564 vs Muse Spark 1.3 at 1442.