Model Comparison

Kimi K2.5 vs GPT-5.4 mini

Both models are evenly matched across the benchmarks. Kimi K2.5 is 1.4x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Kimi K2.5 outperforms in 3 benchmarks (Humanity's Last Exam, MMMU-Pro, OmniDocBench 1.5), while GPT-5.4 mini is better at 3 benchmarks (GPQA, SWE-Bench Pro, Terminal-Bench 2.0).

Both models are evenly matched across the benchmarks.

Sat Apr 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Kimi K2.5 costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) is 1.3x cheaper than GPT-5.4 mini ($0.75/1M tokens).

For output processing, Kimi K2.5 ($3.00/1M tokens) is 1.5x cheaper than GPT-5.4 mini ($4.50/1M tokens).

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

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

Lowest available price from all providers
Sat Apr 18 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$3.00
Best providerFireworks
OpenAI
GPT-5.4 mini
Input tokens$0.75
Output tokens$4.50
Best providerOpenAI
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

GPT-5.4 mini 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 mini is limited to 128,000 tokens.

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

Input Capabilities

Supported data types and modalities

Both Kimi K2.5 and GPT-5.4 mini 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 mini

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while GPT-5.4 mini 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 mini

Proprietary

Closed source

Release Timeline

When each model was launched

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

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

Kimi K2.5

Jan 27, 2026

2 months ago

GPT-5.4 mini

Mar 17, 2026

1 months ago

1mo newer

Knowledge Cutoff

When training data ends

GPT-5.4 mini 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 mini'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 mini

Aug 2025

Provider Availability

Kimi K2.5 is available from Fireworks, Moonshot AI. GPT-5.4 mini is available from OpenAI.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $3.00/1M
moonshot logo
Unknown Organization
Input Price:Input: $0.60/1MOutput Price:Output: $3.00/1M

GPT-5.4 mini

openai logo
OpenAI
Input Price:Input: $0.75/1MOutput Price:Output: $4.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Moonshot AI
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher Humanity's Last Exam score (50.2% vs 28.2%)
Higher MMMU-Pro score (78.5% vs 76.6%)
Higher OmniDocBench 1.5 score (88.8% vs 87.4%)
OpenAI
Larger context window (400,000 tokens)
Higher GPQA score (88.0% vs 87.6%)
Higher SWE-Bench Pro score (54.4% vs 50.7%)
Higher Terminal-Bench 2.0 score (60.0% vs 50.8%)

Detailed Comparison

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

FAQ

Common questions about Kimi K2.5 vs GPT-5.4 mini

Both models are evenly matched across the benchmarks. Kimi K2.5 is made by Moonshot AI and GPT-5.4 mini is made by OpenAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. GPT-5.4 mini scores Tau2 Telecom: 93.4%, GPQA: 88.0%, OmniDocBench 1.5: 87.4%, MMMU-Pro: 76.6%, Graphwalks BFS <128k: 76.3%.
Kimi K2.5 is 1.3x cheaper for input tokens. Kimi K2.5 costs $0.60/M input and $3.00/M output via fireworks. GPT-5.4 mini costs $0.75/M input and $4.50/M output via openai.
Kimi K2.5 supports 262K tokens and GPT-5.4 mini supports 400K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (262K vs 400K), input pricing ($0.60 vs $0.75/M), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and GPT-5.4 mini is developed by OpenAI.