Make AI phone calls with one API call

Start for free

Model Comparison

DeepSeek-V3.2 (Thinking) vs Kimi K2 0905

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is 3.4x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

DeepSeek-V3.2 (Thinking) outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Kimi K2 0905 is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Fri Apr 24 2026 • llm-stats.com

Arena Performance

Human preference votes

CallingBox

Done comparing? Ship the phone agent.

One API for outbound and inbound calls.

Start for freeRead the docs
$0.05 /min all-in7 lines of code

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2 (Thinking) costs less

For input processing, DeepSeek-V3.2 (Thinking) ($0.28/1M tokens) is 2.1x cheaper than Kimi K2 0905 ($0.60/1M tokens).

For output processing, DeepSeek-V3.2 (Thinking) ($0.42/1M tokens) is 6.0x cheaper than Kimi K2 0905 ($2.50/1M tokens).

In conclusion, Kimi K2 0905 is more expensive than DeepSeek-V3.2 (Thinking).*

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

Lowest available price from all providers
Fri Apr 24 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
Moonshot AI
Kimi K2 0905
Input tokens$0.60
Output tokens$2.50
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

315.0B diff

Kimi K2 0905 has 315.0B more parameters than DeepSeek-V3.2 (Thinking), making it 46.0% larger.

DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
Moonshot AI
Kimi K2 0905
1000.0Bparameters
685.0B
DeepSeek-V3.2 (Thinking)
1000.0B
Kimi K2 0905

Context Window

Maximum input and output token capacity

Kimi K2 0905 accepts 262,144 input tokens compared to DeepSeek-V3.2 (Thinking)'s 131,072 tokens. Kimi K2 0905 can generate longer responses up to 262,144 tokens, while DeepSeek-V3.2 (Thinking) is limited to 65,536 tokens.

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
Moonshot AI
Kimi K2 0905
Input262,144 tokens
Output262,144 tokens
Fri Apr 24 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while Kimi K2 0905 uses a proprietary license.

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

DeepSeek-V3.2 (Thinking)

MIT

Open weights

Kimi K2 0905

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while Kimi K2 0905 was released on 2025-09-05.

DeepSeek-V3.2 (Thinking) is 3 months newer than Kimi K2 0905.

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

4 months ago

2mo newer
Kimi K2 0905

Sep 5, 2025

7 months 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-V3.2 (Thinking) is available from DeepSeek. Kimi K2 0905 is available from Novita.

DeepSeek-V3.2 (Thinking)

deepseek logo
DeepSeek
Input Price:Input: $0.28/1MOutput Price:Output: $0.42/1M

Kimi K2 0905

novita logo
Novita
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher GPQA score (82.4% vs 75.8%)
Higher MMLU-Pro score (85.0% vs 82.5%)
Moonshot AI
Larger context window (262,144 tokens)

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek-V3.2 (Thinking)
Moonshot AI
Kimi K2 0905

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs Kimi K2 0905

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is made by DeepSeek and Kimi K2 0905 is made by Moonshot AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. Kimi K2 0905 scores HumanEval: 94.5%, MMLU: 90.2%, MATH: 89.1%, MMLU-Pro: 82.5%, GPQA: 75.8%.
DeepSeek-V3.2 (Thinking) is 2.1x cheaper for input tokens. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek. Kimi K2 0905 costs $0.60/M input and $2.50/M output via novita.
DeepSeek-V3.2 (Thinking) supports 131K tokens and Kimi K2 0905 supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (131K vs 262K), input pricing ($0.28 vs $0.60/M), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.
DeepSeek-V3.2 (Thinking) is developed by DeepSeek and Kimi K2 0905 is developed by Moonshot AI.