The AI arena is free today

Open Superagent

GPT-3.5 Turbo vs Llama 3.2 90B Instruct

Llama 3.2 90B Instruct leads the LLM Stats Score 5.2 to -9.4. Llama 3.2 90B Instruct is 2.1x cheaper per token.

OpenAI · Meta · Updated for 2026

Which is better?

Llama 3.2 90B Instruct leads the overall LLM Stats Score 5.2 to -9.4, ranking #296 overall.

In the 6 individual benchmarks reported for both models, Llama 3.2 90B Instruct wins 6; this is a narrower head-to-head signal than the composite indexes.

On price, Llama 3.2 90B Instruct is roughly 2.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Llama 3.2 90B Instruct also accepts a larger context window (128,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose GPT-3.5 Turbo

  • you want predictable pricing at $0.50/M input and $1.50/M output

Choose Llama 3.2 90B Instruct

  • overall performance matters — it scores 5.2 and ranks #296 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 6 of 6 exact shared results
  • cost matters — it's about 2.1x cheaper per token
  • you process long inputs — it offers a 128,000 token context window
  • you want the most recent training data — it shipped Sep 2024
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

GPT-3.5 Turbo
OpenAI
Llama 3.2 90B Instruct
Meta
Core performance indexes
LLM Stats Score
-9.4
#363
5.2
#296
Reasoning
-8.7
#356
6.7
#284
Cost, coverage & limits
Benchmark wins
0 of 6
6 of 6
Input price
$0.50 / M
$0.35 / M
Output price
$1.50 / M
$0.40 / M
Context window
16,385
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
GPT-3.5 Turbo
Llama 3.2 90B Instruct
Math
-2.3#309
11.6#238
Vision
-16.2#208
2.8#165
Multimodal
-14.4#168
5.6#136
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

8 reported for GPT-3.5 Turbo · 13 for Llama 3.2 90B Instruct

6 shared

GPT-3.5 Turbo outperforms in 0 benchmarks, while Llama 3.2 90B Instruct is better at 6 benchmarks (GPQA, MATH, MathVista, MGSM, MMLU, MMMU).

Llama 3.2 90B Instruct significantly outperforms across most benchmarks.

Tue Sep 15 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Llama 3.2 90B Instruct costs less

For input processing, GPT-3.5 Turbo ($0.50/1M tokens) is 1.4x more expensive than Llama 3.2 90B Instruct ($0.35/1M tokens).

For output processing, GPT-3.5 Turbo ($1.50/1M tokens) is 3.8x more expensive than Llama 3.2 90B Instruct ($0.40/1M tokens).

In conclusion, GPT-3.5 Turbo 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
Tue Sep 15 2026 • llm-stats.com
OpenAI
GPT-3.5 Turbo
Input tokens$0.50
Output tokens$1.50
Best providerAzure
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

Llama 3.2 90B Instruct accepts 128,000 input tokens compared to GPT-3.5 Turbo's 16,385 tokens. Llama 3.2 90B Instruct can generate longer responses up to 128,000 tokens, while GPT-3.5 Turbo is limited to 4,096 tokens.

OpenAI
GPT-3.5 Turbo
Input16,385 tokens
Output4,096 tokens
Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Tue Sep 15 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Llama 3.2 90B Instruct supports multimodal inputs, whereas GPT-3.5 Turbo does not.

Llama 3.2 90B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-3.5 Turbo

Text
Images
Audio
Video

Llama 3.2 90B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-3.5 Turbo 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.

GPT-3.5 Turbo

Proprietary

Closed source

Llama 3.2 90B Instruct

Llama 3.2

Open weights

Release Timeline

When each model was launched

GPT-3.5 Turbo was released on 2023-03-21, while Llama 3.2 90B Instruct was released on 2024-09-25.

Llama 3.2 90B Instruct is 18 months newer than GPT-3.5 Turbo.

GPT-3.5 Turbo

Mar 21, 2023

3.5 years ago

Llama 3.2 90B Instruct

Sep 25, 2024

2.0 years ago

1.5yr newer

Knowledge Cutoff

When training data ends

GPT-3.5 Turbo has a documented knowledge cutoff of 2021-09-30, while Llama 3.2 90B Instruct's cutoff date is not specified.

We can confirm GPT-3.5 Turbo's training data extends to 2021-09-30, but cannot make a direct comparison without Llama 3.2 90B Instruct's cutoff date.

GPT-3.5 Turbo

Sep 2021

Llama 3.2 90B Instruct

—

Provider Availability

GPT-3.5 Turbo is available from Azure, OpenAI. Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic.

GPT-3.5 Turbo

azure logo
Azure
Input Price:Input: $0.50/1MOutput Price:Output: $1.50/1M
openai logo
OpenAI
Input Price:Input: $0.50/1MOutput Price:Output: $1.50/1M

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→

Judge for yourself.

Run your own prompts against GPT-3.5 Turbo and Llama 3.2 90B Instruct side-by-side, then vote on the output you prefer.

GPT-3.5 Turbo
✓ Preferred
Llama 3.2 90B Instruct
Open in Playground

FAQ

Common questions about GPT-3.5 Turbo vs Llama 3.2 90B Instruct.

Which is better, GPT-3.5 Turbo or Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct leads the LLM Stats Score 5.2 to -9.4. GPT-3.5 Turbo is made by OpenAI and Llama 3.2 90B Instruct is made by Meta. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-3.5 Turbo compare to Llama 3.2 90B Instruct in benchmarks?

GPT-3.5 Turbo scores DROP: 70.2%, MMLU: 69.8%, HumanEval: 68.0%, MGSM: 56.3%, MATH: 43.1%. Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%.

Is GPT-3.5 Turbo cheaper than Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct is 1.4x cheaper for input tokens. GPT-3.5 Turbo costs $0.50/M input and $1.50/M output via azure. Llama 3.2 90B Instruct costs $0.35/M input and $0.40/M output via deepinfra.

What are the context window sizes for GPT-3.5 Turbo and Llama 3.2 90B Instruct?

GPT-3.5 Turbo supports 16K 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 GPT-3.5 Turbo and Llama 3.2 90B Instruct?

Key differences include LLM Stats Score (-9.4 vs 5.2), context window (16K vs 128K), input pricing ($0.50 vs $0.35/M), multimodal support (no vs yes), licensing (Proprietary vs Llama 3.2). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-3.5 Turbo and Llama 3.2 90B Instruct?

GPT-3.5 Turbo is developed by OpenAI and Llama 3.2 90B Instruct is developed by Meta.

Related comparisons