The AI arena is free today

Open Superagent

DeepSeek-V3.2-Exp vs Gemini 2.5 Pro Preview 06-05

DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05 are closely matched at 28.2 and 29.9 on the LLM Stats Score. DeepSeek-V3.2-Exp is 11.3x cheaper per token.

DeepSeek · Google · Updated for 2026

Which is better?

DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05 are closely matched on the overall LLM Stats Score at 28.2 and 29.9.

In the 7 individual benchmarks reported for both models, DeepSeek-V3.2-Exp wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, DeepSeek-V3.2-Exp is roughly 11.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Gemini 2.5 Pro Preview 06-05 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-V3.2-Exp

  • you value its reported benchmark strengths — it wins 4 of 7 exact shared results
  • cost matters — it's about 11.3x cheaper per token
  • you want the most recent training data — it shipped Sep 2025
  • you need open weights you can self-host or fine-tune

Choose Gemini 2.5 Pro Preview 06-05

  • you process long inputs — it offers a 1,048,576 token context window

At a glance

The differences that matter most.

DeepSeek-V3.2-Exp
DeepSeek
Gemini 2.5 Pro Preview 06-05
Google
Core performance indexes
LLM Stats Score
28.2
#134
29.9
#122
Reasoning
28.1
#130
28.4
#129
Coding
17.5
#119
16.7
#124
Cost, coverage & limits
Benchmark wins
4 of 7
3 of 7
Input price
$0.27 / M
$1.25 / M
Output price
$0.41 / M
$10.00 / M
Context window
163,840
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek-V3.2-Exp
Gemini 2.5 Pro Preview 06-05
Math
26.3#103
22.0#142
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for DeepSeek-V3.2-Exp · 13 for Gemini 2.5 Pro Preview 06-05

7 shared

DeepSeek-V3.2-Exp outperforms in 4 benchmarks (AIME 2025, LiveCodeBench, SimpleQA, SWE-Bench Verified), while Gemini 2.5 Pro Preview 06-05 is better at 3 benchmarks (Aider-Polyglot, GPQA, Humanity's Last Exam).

DeepSeek-V3.2-Exp has a slight edge in benchmark performance.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2-Exp costs less

For input processing, DeepSeek-V3.2-Exp ($0.27/1M tokens) is 4.6x cheaper than Gemini 2.5 Pro Preview 06-05 ($1.25/1M tokens).

For output processing, DeepSeek-V3.2-Exp ($0.41/1M tokens) is 24.4x cheaper than Gemini 2.5 Pro Preview 06-05 ($10.00/1M tokens).

In conclusion, Gemini 2.5 Pro Preview 06-05 is more expensive than DeepSeek-V3.2-Exp.*

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

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2-Exp
Input tokens$0.27
Output tokens$0.41
Best providerNovita
Google
Gemini 2.5 Pro Preview 06-05
Input tokens$1.25
Output tokens$10.00
Best providerGoogle
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Gemini 2.5 Pro Preview 06-05 accepts 1,048,576 input tokens compared to DeepSeek-V3.2-Exp's 163,840 tokens. DeepSeek-V3.2-Exp can generate longer responses up to 65,536 tokens, while Gemini 2.5 Pro Preview 06-05 is limited to 65,535 tokens.

DeepSeek
DeepSeek-V3.2-Exp
Input163,840 tokens
Output65,536 tokens
Google
Gemini 2.5 Pro Preview 06-05
Input1,048,576 tokens
Output65,535 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 2.5 Pro Preview 06-05 supports multimodal inputs, whereas DeepSeek-V3.2-Exp does not.

Gemini 2.5 Pro Preview 06-05 can handle both text and other forms of data like images, making it suitable for multimodal applications.

DeepSeek-V3.2-Exp

Text
Images
Audio
Video

Gemini 2.5 Pro Preview 06-05

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V3.2-Exp is licensed under MIT, while Gemini 2.5 Pro Preview 06-05 uses a proprietary license.

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

DeepSeek-V3.2-Exp

MIT

Open weights

Gemini 2.5 Pro Preview 06-05

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V3.2-Exp was released on 2025-09-29, while Gemini 2.5 Pro Preview 06-05 was released on 2025-06-05.

DeepSeek-V3.2-Exp is 4 months newer than Gemini 2.5 Pro Preview 06-05.

DeepSeek-V3.2-Exp

Sep 29, 2025

11 months ago

3mo newer
Gemini 2.5 Pro Preview 06-05

Jun 5, 2025

1.3 years ago

Knowledge Cutoff

When training data ends

Gemini 2.5 Pro Preview 06-05 has a documented knowledge cutoff of 2025-01-31, while DeepSeek-V3.2-Exp's cutoff date is not specified.

We can confirm Gemini 2.5 Pro Preview 06-05's training data extends to 2025-01-31, but cannot make a direct comparison without DeepSeek-V3.2-Exp's cutoff date.

DeepSeek-V3.2-Exp

—

Gemini 2.5 Pro Preview 06-05

Jan 2025

Provider Availability

DeepSeek-V3.2-Exp is available from Novita. Gemini 2.5 Pro Preview 06-05 is available from Google.

DeepSeek-V3.2-Exp

novita logo
Novita
Input Price:Input: $0.27/1MOutput Price:Output: $0.41/1M

Gemini 2.5 Pro Preview 06-05

google logo
Google
Input Price:Input: $1.25/1MOutput Price:Output: $10.00/1M
* 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 DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05 side-by-side, then vote on the output you prefer.

DeepSeek-V3.2-Exp
✓ Preferred
Gemini 2.5 Pro Preview 06-05
Open in Playground

FAQ

Common questions about DeepSeek-V3.2-Exp vs Gemini 2.5 Pro Preview 06-05.

Which is better, DeepSeek-V3.2-Exp or Gemini 2.5 Pro Preview 06-05?

DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05 are closely matched on the LLM Stats Score at 28.2 and 29.9. DeepSeek-V3.2-Exp is made by DeepSeek and Gemini 2.5 Pro Preview 06-05 is made by Google. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V3.2-Exp compare to Gemini 2.5 Pro Preview 06-05 in benchmarks?

DeepSeek-V3.2-Exp scores SimpleQA: 97.1%, AIME 2025: 89.3%, MMLU-Pro: 85.0%, HMMT 2025: 83.6%, GPQA: 79.9%. Gemini 2.5 Pro Preview 06-05 scores Global-MMLU-Lite: 89.2%, AIME 2025: 88.0%, FACTS Grounding: 87.8%, GPQA: 86.4%, VideoMMMU: 83.6%.

Is DeepSeek-V3.2-Exp cheaper than Gemini 2.5 Pro Preview 06-05?

DeepSeek-V3.2-Exp is 4.6x cheaper for input tokens. DeepSeek-V3.2-Exp costs $0.27/M input and $0.41/M output via novita. Gemini 2.5 Pro Preview 06-05 costs $1.25/M input and $10.00/M output via google.

What are the context window sizes for DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05?

DeepSeek-V3.2-Exp supports 164K tokens and Gemini 2.5 Pro Preview 06-05 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05?

Key differences include LLM Stats Score (28.2 vs 29.9), context window (164K vs 1.0M), input pricing ($0.27 vs $1.25/M), multimodal support (no vs yes), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2-Exp and Gemini 2.5 Pro Preview 06-05?

DeepSeek-V3.2-Exp is developed by DeepSeek and Gemini 2.5 Pro Preview 06-05 is developed by Google.

Related comparisons