Gemini 1.5 Pro vs Llama 4 Scout: Specs & Benchmark Comparison

Gemini 1.5 Pro is developed by Google, while Llama 4 Scout comes from Meta. Gemini 1.5 Pro was released in May 2024, and Llama 4 Scout followed 11 months later in April 2025. Llama 4 Scout has a published size of about 109 billion parameters; Google has not disclosed the parameter count of Gemini 1.5 Pro.

The two models share 7 published benchmarks. Gemini 1.5 Pro leads on 4 of them, Llama 4 Scout on 3. The widest gaps are on MATH, where Gemini 1.5 Pro scores 86.5% against 50.3%; MMLU, where Gemini 1.5 Pro scores 85.9% against 79.6%. Averaged across everything we track, Gemini 1.5 Pro sits at 72.6% and Llama 4 Scout at 67.3%.

Llama 4 Scout is the cheaper API at $0.18 per million input tokens and $0.59 per million output tokens, roughly 14 times cheaper than Gemini 1.5 Pro at $2.50 and $10. Llama 4 Scout takes the larger context window at 10M tokens, compared with 2M for Gemini 1.5 Pro. Both accept text and images as input.

CharacteristicGemini 1.5 ProLlama 4 Scout
CompanyGoogleMeta
Release DateMay 1, 2024April 5, 2025
Parameters109B
MultimodalYesYes
Context (input)2.1M10.0M
Context (output)8K10.0M
Input Price / 1M$2.50$0.18
Output Price / 1M$10.00$0.59
Average Score72.6%67.3%
Benchmarks
MATH86.5%50.3%
MMLU85.9%79.6%
MMMU65.9%69.4%
MGSM87.5%90.6%
MathVista68.1%70.7%
GPQA59.1%57.2%
MMLU-Pro75.8%74.3%

Visual Benchmark Comparison

Gemini 1.5 Pro
Llama 4 Scout
MATH0.9 vs 0.5
0.9
0.5
MMLU0.9 vs 0.8
0.9
0.8
MMMU0.7 vs 0.7
0.7
0.7
MGSM0.9 vs 0.9
0.9
0.9
MathVista0.7 vs 0.7
0.7
0.7
GPQA0.6 vs 0.6
0.6
0.6
MMLU-Pro0.8 vs 0.7
0.8
0.7

Verdict

Llama 4 Scout leads in 3 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: Gemini 1.5 Pro — 0.7, Llama 4 Scout — 0.7.

API Cost

Llama 4 Scout is 16.2x cheaper: input $0.18/1M vs $2.50/1M tokens.

Context Window

Llama 4 Scout supports a larger context: 10M vs 2M tokens.

Recency

Llama 4 Scout is newer: released 4/5/2025 vs 5/1/2024.

More About These Models

Frequently Asked Questions

Which is better for coding — Gemini 1.5 Pro or Llama 4 Scout?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Gemini 1.5 Pro or Llama 4 Scout?
Llama 4 Scout is cheaper for input: $0.18 per 1M tokens vs $2.50.
Which has a larger context window — Gemini 1.5 Pro or Llama 4 Scout?
Llama 4 Scout supports a larger context: 10,000,000 tokens vs 2,097,152.

The Gemini 1.5 Pro and Llama 4 Scout comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Gemini 1.5 Pro or Llama 4 Scout page. See also the complete list of AI model comparisons.