The AI arena is free today

Open Superagent

DeepSeek-V4.1-Flash-1017 vs Llama 3.2 90B Instruct

DeepSeek-V4.1-Flash-1017 leads the LLM Stats Score 51.0 to 4.9. Llama 3.2 90B Instruct is 1.4x cheaper per token.

DeepSeek · Meta · Updated for 2026

Which is better?

DeepSeek-V4.1-Flash-1017 leads the overall LLM Stats Score 51.0 to 4.9, ranking #15 overall.

On price, Llama 3.2 90B Instruct is roughly 1.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V4.1-Flash-1017 also accepts a larger context window (1,048,576 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 DeepSeek-V4.1-Flash-1017

  • overall performance matters — it scores 51.0 and ranks #15 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Oct 2026

Choose Llama 3.2 90B Instruct

  • cost matters — it's about 1.4x cheaper per token

At a glance

The differences that matter most.

DeepSeek-V4.1-Flash-1017
DeepSeek
Llama 3.2 90B Instruct
Meta
Core performance indexes
LLM Stats Score
51.0
#15
4.9
#321
Reasoning
48.6
#18
6.4
#309
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.30 / M
$0.35 / M
Output price
$1.20 / M
$0.40 / M
Context window
1,048,576
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
DeepSeek-V4.1-Flash-1017
Llama 3.2 90B Instruct
Math
31.8#67
11.5#250
Vision
32.2#26
2.8#184
Multimodal
35.0#14
5.5#155
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for DeepSeek-V4.1-Flash-1017 · 13 for Llama 3.2 90B Instruct

No common benchmarks found

DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

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, DeepSeek-V4.1-Flash-1017 ($0.30/1M tokens) is 1.2x cheaper than Llama 3.2 90B Instruct ($0.35/1M tokens).

For output processing, DeepSeek-V4.1-Flash-1017 ($1.20/1M tokens) is 3.0x more expensive than Llama 3.2 90B Instruct ($0.40/1M tokens).

In conclusion, DeepSeek-V4.1-Flash-1017 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
Mon Oct 19 2026 • llm-stats.com
DeepSeek
DeepSeek-V4.1-Flash-1017
Input tokens$0.30
Output tokens$1.20
Best providerDeepSeek
Meta
Llama 3.2 90B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Notice missing or incorrect data?

Model Size

Parameter count comparison

673.2B diff

DeepSeek-V4.1-Flash-1017 has 673.2B more parameters than Llama 3.2 90B Instruct, making it 748.0% larger.

DeepSeek
DeepSeek-V4.1-Flash-1017
763.2Bparameters
Meta
Llama 3.2 90B Instruct
90.0Bparameters
763.2B
DeepSeek-V4.1-Flash-1017
90.0B
Llama 3.2 90B Instruct

Context Window

Maximum input and output token capacity

DeepSeek-V4.1-Flash-1017 accepts 1,048,576 input tokens compared to Llama 3.2 90B Instruct's 128,000 tokens. DeepSeek-V4.1-Flash-1017 can generate longer responses up to 393,216 tokens, while Llama 3.2 90B Instruct is limited to 128,000 tokens.

DeepSeek
DeepSeek-V4.1-Flash-1017
Input1,048,576 tokens
Output393,216 tokens
Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Mon Oct 19 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instruct support multimodal inputs.

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

DeepSeek-V4.1-Flash-1017

Text
Images
Audio
Video

Llama 3.2 90B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V4.1-Flash-1017 is licensed under MIT, 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.

DeepSeek-V4.1-Flash-1017

MIT

Open weights

Llama 3.2 90B Instruct

Llama 3.2

Open weights

Release Timeline

When each model was launched

DeepSeek-V4.1-Flash-1017 was released on 2026-10-17, while Llama 3.2 90B Instruct was released on 2024-09-25.

DeepSeek-V4.1-Flash-1017 is 25 months newer than Llama 3.2 90B Instruct.

DeepSeek-V4.1-Flash-1017

Oct 17, 2026

2 days ago

2.1yr newer
Llama 3.2 90B Instruct

Sep 25, 2024

2.1 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V4.1-Flash-1017 is available from DeepSeek. Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic.

DeepSeek-V4.1-Flash-1017

deepseek logo
DeepSeek
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M

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?

Judge for yourself.

Run your own prompts against DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instruct side-by-side, then vote on the output you prefer.

DeepSeek-V4.1-Flash-1017
✓ Preferred
Llama 3.2 90B Instruct
Open in Playground

FAQ

Common questions about DeepSeek-V4.1-Flash-1017 vs Llama 3.2 90B Instruct.

Which is better, DeepSeek-V4.1-Flash-1017 or Llama 3.2 90B Instruct?

DeepSeek-V4.1-Flash-1017 leads the LLM Stats Score 51.0 to 4.9. DeepSeek-V4.1-Flash-1017 is made by DeepSeek 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 DeepSeek-V4.1-Flash-1017 compare to Llama 3.2 90B Instruct in benchmarks?

DeepSeek-V4.1-Flash-1017 scores BabyVision: 92.5%, Chartography: 83.0%, DeepSWE 1.1: 77.0%, NL2Repo: 68.2%, AutomationBench: 60.5%. Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%.

Is DeepSeek-V4.1-Flash-1017 cheaper than Llama 3.2 90B Instruct?

DeepSeek-V4.1-Flash-1017 is 1.2x cheaper for input tokens. DeepSeek-V4.1-Flash-1017 costs $0.30/M input and $1.20/M output via deepseek. Llama 3.2 90B Instruct costs $0.35/M input and $0.40/M output via deepinfra.

What are the context window sizes for DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instruct?

DeepSeek-V4.1-Flash-1017 supports 1.0M 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 DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instruct?

Key differences include LLM Stats Score (51.0 vs 4.9), context window (1.0M vs 128K), input pricing ($0.30 vs $0.35/M), licensing (MIT vs Llama 3.2). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4.1-Flash-1017 and Llama 3.2 90B Instruct?

DeepSeek-V4.1-Flash-1017 is developed by DeepSeek and Llama 3.2 90B Instruct is developed by Meta.

Related comparisons