Model Comparison

GPT-5 vs Kimi K2-Instruct-0905

GPT-5 significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

11 benchmarks

GPT-5 outperforms in 11 benchmarks (Aider-Polyglot, AIME 2025, GPQA, HMMT 2025, Humanity's Last Exam, MMLU, Multi-Challenge, SWE-Bench Verified, Tau2 Airline, Tau2 Retail, Tau2 Telecom), while Kimi K2-Instruct-0905 is better at 0 benchmarks.

GPT-5 significantly outperforms across most benchmarks.

Tue Apr 21 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Tue Apr 21 2026 • llm-stats.com
OpenAI
GPT-5
Input tokens$1.25
Output tokens$10.00
Best providerOpenAI
Moonshot AI
Kimi K2-Instruct-0905
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Only GPT-5 specifies input context (400,000 tokens). Only GPT-5 specifies output context (128,000 tokens).

OpenAI
GPT-5
Input400,000 tokens
Output128,000 tokens
Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
Tue Apr 21 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

GPT-5 supports multimodal inputs, whereas Kimi K2-Instruct-0905 does not.

GPT-5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5

Text
Images
Audio
Video

Kimi K2-Instruct-0905

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-5 is licensed under a proprietary license, while Kimi K2-Instruct-0905 uses MIT.

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

GPT-5

Proprietary

Closed source

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

GPT-5 was released on 2025-08-07, while Kimi K2-Instruct-0905 was released on 2025-09-05.

Kimi K2-Instruct-0905 is 1 month newer than GPT-5.

GPT-5

Aug 7, 2025

8 months ago

Kimi K2-Instruct-0905

Sep 5, 2025

7 months ago

4w newer

Knowledge Cutoff

When training data ends

GPT-5 has a documented knowledge cutoff of 2024-09-30, while Kimi K2-Instruct-0905's cutoff date is not specified.

We can confirm GPT-5's training data extends to 2024-09-30, but cannot make a direct comparison without Kimi K2-Instruct-0905's cutoff date.

GPT-5

Sep 2024

Kimi K2-Instruct-0905

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

OpenAI
Larger context window (400,000 tokens)
Supports multimodal inputs
Higher Aider-Polyglot score (88.0% vs 60.0%)
Higher AIME 2025 score (94.6% vs 49.5%)
Higher GPQA score (85.7% vs 75.1%)
Higher HMMT 2025 score (93.3% vs 38.8%)
Higher Humanity's Last Exam score (24.8% vs 4.7%)
Higher MMLU score (92.5% vs 89.5%)
Higher Multi-Challenge score (69.6% vs 54.1%)
Higher SWE-Bench Verified score (74.9% vs 65.8%)
Higher Tau2 Airline score (62.6% vs 56.5%)
Higher Tau2 Retail score (81.1% vs 70.6%)
Higher Tau2 Telecom score (96.7% vs 65.8%)
Moonshot AI
Has open weights

Detailed Comparison

AI Model Comparison Table
Feature
OpenAI
GPT-5
Moonshot AI
Kimi K2-Instruct-0905

FAQ

Common questions about GPT-5 vs Kimi K2-Instruct-0905

GPT-5 significantly outperforms across most benchmarks. GPT-5 is made by OpenAI and Kimi K2-Instruct-0905 is made by Moonshot AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
GPT-5 scores SWE-Lancer (IC-Diamond subset): 100.0%, COLLIE: 99.0%, Tau2 Telecom: 96.7%, OpenAI-MRCR: 2 needle 128k: 95.2%, AIME 2025: 94.6%. Kimi K2-Instruct-0905 scores MATH-500: 97.4%, MMLU-Redux: 92.7%, IFEval: 89.8%, AutoLogi: 89.5%, MMLU: 89.5%.
GPT-5 supports 400K tokens and Kimi K2-Instruct-0905 supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.
GPT-5 is developed by OpenAI and Kimi K2-Instruct-0905 is developed by Moonshot AI.