Model Comparison

Gemini 1.5 Pro vs Llama 3.2 90B InstructWhich is better in 2026?

Gemini 1.5 Pro significantly outperforms across most benchmarks. Llama 3.2 90B Instruct is 12.1x cheaper per token.

Verdict: Gemini 1.5 Pro vs Llama 3.2 90B Instruct — which is better?

Gemini 1.5 Pro (by Google) and Llama 3.2 90B Instruct (by Meta) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Gemini 1.5 Pro outperforms in 5 benchmarks (GPQA, MATH, MathVista, MGSM, MMMU), while Llama 3.2 90B Instruct is better at 1 benchmark (MMLU). Gemini 1.5 Pro significantly outperforms across most benchmarks.

On price, Llama 3.2 90B Instruct is roughly 12.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Gemini 1.5 Pro also accepts a larger context window (2,097,152 input tokens), making it the stronger choice for long documents and large codebases.

Choose Gemini 1.5 Pro if…

  • you want the strongest raw capability — it leads on 5 of 6 shared benchmarks
  • you process long inputs — it offers a 2,097,152 token context window

Choose Llama 3.2 90B Instruct if…

  • cost matters — it's about 12.1x cheaper per token
  • you want the most recent training data — it shipped Sep 2024
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Gemini 1.5 Pro outperforms in 5 benchmarks (GPQA, MATH, MathVista, MGSM, MMMU), while Llama 3.2 90B Instruct is better at 1 benchmark (MMLU).

Gemini 1.5 Pro significantly outperforms across most benchmarks.

Thu Jul 02 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Llama 3.2 90B Instruct costs less

For input processing, Gemini 1.5 Pro ($2.50/1M tokens) is 7.1x more expensive than Llama 3.2 90B Instruct ($0.35/1M tokens).

For output processing, Gemini 1.5 Pro ($10.00/1M tokens) is 25.0x more expensive than Llama 3.2 90B Instruct ($0.40/1M tokens).

In conclusion, Gemini 1.5 Pro is more expensive than Llama 3.2 90B Instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Thu Jul 02 2026 • llm-stats.com
Google
Gemini 1.5 Pro
Input tokens$2.50
Output tokens$10.00
Best providerGoogle
Meta
Llama 3.2 90B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Gemini 1.5 Pro accepts 2,097,152 input tokens compared to Llama 3.2 90B Instruct's 128,000 tokens. Llama 3.2 90B Instruct can generate longer responses up to 128,000 tokens, while Gemini 1.5 Pro is limited to 8,192 tokens.

Google
Gemini 1.5 Pro
Input2,097,152 tokens
Output8,192 tokens
Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Thu Jul 02 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Gemini 1.5 Pro and Llama 3.2 90B Instruct support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Gemini 1.5 Pro

Text
Images
Audio
Video

Llama 3.2 90B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 1.5 Pro is licensed under a proprietary license, while Llama 3.2 90B Instruct uses Llama 3.2.

License differences may affect how you can use these models in commercial or open-source projects.

Gemini 1.5 Pro

Proprietary

Closed source

Llama 3.2 90B Instruct

Llama 3.2

Open weights

Release Timeline

When each model was launched

Gemini 1.5 Pro was released on 2024-05-01, while Llama 3.2 90B Instruct was released on 2024-09-25.

Llama 3.2 90B Instruct is 5 months newer than Gemini 1.5 Pro.

Gemini 1.5 Pro

May 1, 2024

2.2 years ago

Llama 3.2 90B Instruct

Sep 25, 2024

1.8 years ago

4mo newer

Knowledge Cutoff

When training data ends

Gemini 1.5 Pro has a documented knowledge cutoff of 2023-11-01, while Llama 3.2 90B Instruct's cutoff date is not specified.

We can confirm Gemini 1.5 Pro's training data extends to 2023-11-01, but cannot make a direct comparison without Llama 3.2 90B Instruct's cutoff date.

Gemini 1.5 Pro

Nov 2023

Llama 3.2 90B Instruct

—

Provider Availability

Gemini 1.5 Pro is available from Google. Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic.

Gemini 1.5 Pro

google logo
Google
Input Price:Input: $2.50/1MOutput Price:Output: $10.00/1M

Llama 3.2 90B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $0.40/1M
bedrock logo
AWS Bedrock
Input Price:Input: $0.72/1MOutput Price:Output: $0.72/1M
fireworks logo
Fireworks
Input Price:Input: $0.89/1MOutput Price:Output: $0.89/1M
together logo
Together
Input Price:Input: $1.20/1MOutput Price:Output: $1.20/1M
hyperbolic logo
Hyperbolic
Input Price:Input: $2.00/1MOutput Price:Output: $2.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (2,097,152 tokens)
Higher GPQA score (59.1% vs 46.7%)
Higher MATH score (86.5% vs 68.0%)
Higher MathVista score (68.1% vs 57.3%)
Higher MGSM score (87.5% vs 86.9%)
Higher MMMU score (65.9% vs 60.3%)
Meta
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher MMLU score (86.0% vs 85.9%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Gemini 1.5 Pro and Llama 3.2 90B Instruct side-by-side, then vote on the output you prefer.

Gemini 1.5 Pro
✓ Preferred
Llama 3.2 90B Instruct
Open in Playground
AI Model Comparison Table
Feature
Google
Gemini 1.5 Pro
Meta
Llama 3.2 90B Instruct

FAQ

Common questions about Gemini 1.5 Pro vs Llama 3.2 90B Instruct.

Which is better, Gemini 1.5 Pro or Llama 3.2 90B Instruct?

Gemini 1.5 Pro significantly outperforms across most benchmarks. Gemini 1.5 Pro is made by Google and Llama 3.2 90B Instruct is made by Meta. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemini 1.5 Pro compare to Llama 3.2 90B Instruct in benchmarks?

Gemini 1.5 Pro scores XSTest: 98.8%, FLEURS: 93.3%, HellaSwag: 93.3%, GSM8k: 90.8%, BIG-Bench Hard: 89.2%. Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%.

Is Gemini 1.5 Pro cheaper than Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct is 7.1x cheaper for input tokens. Gemini 1.5 Pro costs $2.50/M input and $10.00/M output via google. Llama 3.2 90B Instruct costs $0.35/M input and $0.40/M output via deepinfra.

What are the context window sizes for Gemini 1.5 Pro and Llama 3.2 90B Instruct?

Gemini 1.5 Pro supports 2.1M tokens and Llama 3.2 90B Instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemini 1.5 Pro and Llama 3.2 90B Instruct?

Key differences include context window (2.1M vs 128K), input pricing ($2.50 vs $0.35/M), licensing (Proprietary vs Llama 3.2). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 1.5 Pro and Llama 3.2 90B Instruct?

Gemini 1.5 Pro is developed by Google and Llama 3.2 90B Instruct is developed by Meta.

Related comparisons