Kimi K2.5 vs GPT-5.4 nano Comparison

Comparing Kimi K2.5 and GPT-5.4 nano across benchmarks, pricing, and capabilities.

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Kimi K2.5 outperforms in 5 benchmarks (GPQA, Humanity's Last Exam, MMMU-Pro, OmniDocBench 1.5, Terminal-Bench 2.0), while GPT-5.4 nano is better at 1 benchmark (SWE-Bench Pro).

Kimi K2.5 significantly outperforms across most benchmarks.

Wed Mar 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

GPT-5.4 nano costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) is 3.0x more expensive than GPT-5.4 nano ($0.20/1M tokens).

For output processing, Kimi K2.5 ($2.50/1M tokens) is 2.0x more expensive than GPT-5.4 nano ($1.25/1M tokens).

In conclusion, Kimi K2.5 is more expensive than GPT-5.4 nano.*

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

Lowest available price from all providers
Wed Mar 18 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$2.50
Best providerFireworks
OpenAI
GPT-5.4 nano
Input tokens$0.20
Output tokens$1.25
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-5.4 nano accepts 400,000 input tokens compared to Kimi K2.5's 262,100 tokens. Kimi K2.5 can generate longer responses up to 262,100 tokens, while GPT-5.4 nano is limited to 128,000 tokens.

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
OpenAI
GPT-5.4 nano
Input400,000 tokens
Output128,000 tokens
Wed Mar 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Kimi K2.5 and GPT-5.4 nano support multimodal inputs.

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

Kimi K2.5

Text
Images
Audio
Video

GPT-5.4 nano

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while GPT-5.4 nano uses a proprietary license.

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

Kimi K2.5

MIT

Open weights

GPT-5.4 nano

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while GPT-5.4 nano was released on 2026-03-17.

GPT-5.4 nano is 2 months newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

1 months ago

GPT-5.4 nano

Mar 17, 2026

1 days ago

1mo newer

Knowledge Cutoff

When training data ends

GPT-5.4 nano has a documented knowledge cutoff of 2025-08-31, while Kimi K2.5's cutoff date is not specified.

We can confirm GPT-5.4 nano's training data extends to 2025-08-31, but cannot make a direct comparison without Kimi K2.5's cutoff date.

Kimi K2.5

GPT-5.4 nano

Aug 2025

Provider Availability

Kimi K2.5 is available from Fireworks. GPT-5.4 nano is available from OpenAI. The availability of providers can affect quality of the model and reliability.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

GPT-5.4 nano

openai logo
OpenAI
Input Price:Input: $0.20/1MOutput Price:Output: $1.25/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Has open weights
Higher GPQA score (87.6% vs 82.8%)
Higher Humanity's Last Exam score (50.2% vs 24.3%)
Higher MMMU-Pro score (78.5% vs 66.1%)
Higher OmniDocBench 1.5 score (88.8% vs 75.8%)
Higher Terminal-Bench 2.0 score (50.8% vs 46.3%)
Larger context window (400,000 tokens)
Less expensive input tokens
Less expensive output tokens
Higher SWE-Bench Pro score (52.4% vs 50.7%)

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
OpenAI
GPT-5.4 nano