Model Comparison

Gemini 2.0 Flash Thinking vs Llama 3.2 90B Instruct

Gemini 2.0 Flash Thinking significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

Gemini 2.0 Flash Thinking outperforms in 2 benchmarks (GPQA, MMMU), while Llama 3.2 90B Instruct is better at 0 benchmarks.

Gemini 2.0 Flash Thinking significantly outperforms across most benchmarks.

Mon Mar 30 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Mon Mar 30 2026 • llm-stats.com
Google
Gemini 2.0 Flash Thinking
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
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

Only Llama 3.2 90B Instruct specifies input context (128,000 tokens). Only Llama 3.2 90B Instruct specifies output context (128,000 tokens).

Google
Gemini 2.0 Flash Thinking
Input- tokens
Output- tokens
Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Mon Mar 30 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Gemini 2.0 Flash Thinking and Llama 3.2 90B Instruct support multimodal inputs.

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

Gemini 2.0 Flash Thinking

Text
Images
Audio
Video

Llama 3.2 90B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 2.0 Flash Thinking 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 2.0 Flash Thinking

Proprietary

Closed source

Llama 3.2 90B Instruct

Llama 3.2

Open weights

Release Timeline

When each model was launched

Gemini 2.0 Flash Thinking was released on 2025-01-21, while Llama 3.2 90B Instruct was released on 2024-09-25.

Gemini 2.0 Flash Thinking is 4 months newer than Llama 3.2 90B Instruct.

Gemini 2.0 Flash Thinking

Jan 21, 2025

1.2 years ago

3mo newer
Llama 3.2 90B Instruct

Sep 25, 2024

1.5 years ago

Knowledge Cutoff

When training data ends

Gemini 2.0 Flash Thinking has a documented knowledge cutoff of 2024-08-01, while Llama 3.2 90B Instruct's cutoff date is not specified.

We can confirm Gemini 2.0 Flash Thinking's training data extends to 2024-08-01, but cannot make a direct comparison without Llama 3.2 90B Instruct's cutoff date.

Gemini 2.0 Flash Thinking

Aug 2024

Llama 3.2 90B Instruct

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Higher GPQA score (74.2% vs 46.7%)
Higher MMMU score (75.4% vs 60.3%)
Meta
Larger context window (128,000 tokens)
Has open weights

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemini 2.0 Flash Thinking
Meta
Llama 3.2 90B Instruct

FAQ

Common questions about Gemini 2.0 Flash Thinking vs Llama 3.2 90B Instruct

Gemini 2.0 Flash Thinking significantly outperforms across most benchmarks. Gemini 2.0 Flash Thinking 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.
Gemini 2.0 Flash Thinking scores MMMU: 75.4%, GPQA: 74.2%, AIME 2024: 73.3%. Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%.
Gemini 2.0 Flash Thinking supports an unknown number of 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.
Key differences include licensing (Proprietary vs Llama 3.2). See the full comparison above for benchmark-by-benchmark results.
Gemini 2.0 Flash Thinking is developed by Google and Llama 3.2 90B Instruct is developed by Meta.