Model Comparison

GPT-4 Turbo vs Kimi K2-Thinking-0905

Kimi K2-Thinking-0905 significantly outperforms across most benchmarks. Kimi K2-Thinking-0905 is 17.6x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

GPT-4 Turbo outperforms in 0 benchmarks, while Kimi K2-Thinking-0905 is better at 1 benchmark (GPQA).

Kimi K2-Thinking-0905 significantly outperforms across most benchmarks.

Sun May 31 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Kimi K2-Thinking-0905 costs less

For input processing, GPT-4 Turbo ($10.00/1M tokens) is 21.3x more expensive than Kimi K2-Thinking-0905 ($0.47/1M tokens).

For output processing, GPT-4 Turbo ($30.00/1M tokens) is 15.0x more expensive than Kimi K2-Thinking-0905 ($2.00/1M tokens).

In conclusion, GPT-4 Turbo is more expensive than Kimi K2-Thinking-0905.*

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

Lowest available price from all providers

Sun May 31 2026 • llm-stats.com

GPT-4 Turbo

Input tokens$10.00

Output tokens$30.00

Best providerAzure

Kimi K2-Thinking-0905

Input tokens$0.47

Output tokens$2.00

Best providerDeepinfra

Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Kimi K2-Thinking-0905 accepts 262,144 input tokens compared to GPT-4 Turbo's 128,000 tokens. Kimi K2-Thinking-0905 can generate longer responses up to 262,144 tokens, while GPT-4 Turbo is limited to 4,096 tokens.

GPT-4 Turbo

Input128,000 tokens

Output4,096 tokens

Kimi K2-Thinking-0905

Input262,144 tokens

Output262,144 tokens

Sun May 31 2026 • llm-stats.com

License

Usage and distribution terms

GPT-4 Turbo is licensed under a proprietary license, while Kimi K2-Thinking-0905 uses MIT.

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

GPT-4 Turbo

Proprietary

Closed source

Kimi K2-Thinking-0905

MIT

Open weights

Release Timeline

When each model was launched

GPT-4 Turbo was released on 2024-04-09, while Kimi K2-Thinking-0905 was released on 2025-09-05.

Kimi K2-Thinking-0905 is 17 months newer than GPT-4 Turbo.

GPT-4 Turbo

Apr 9, 2024

2.1 years ago

Kimi K2-Thinking-0905

Sep 5, 2025

8 months ago

1.4yr newer

Knowledge Cutoff

When training data ends

GPT-4 Turbo has a documented knowledge cutoff of 2023-12-31, while Kimi K2-Thinking-0905's cutoff date is not specified.

We can confirm GPT-4 Turbo's training data extends to 2023-12-31, but cannot make a direct comparison without Kimi K2-Thinking-0905's cutoff date.

GPT-4 Turbo

Dec 2023

Kimi K2-Thinking-0905

—

Provider Availability

GPT-4 Turbo is available from Azure, OpenAI. Kimi K2-Thinking-0905 is available from DeepInfra, Novita, Fireworks.

GPT-4 Turbo

Azure

Input Price:Input: $10.00/1MOutput Price:Output: $30.00/1M

OpenAI

Input Price:Input: $10.00/1MOutput Price:Output: $30.00/1M

Kimi K2-Thinking-0905

Deepinfra

Input Price:Input: $0.47/1MOutput Price:Output: $2.00/1M

Novita

Input Price:Input: $0.48/1MOutput Price:Output: $2.00/1M

Fireworks

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

GPT-4 Turbo

View details

OpenAI

No standout differentiators in the data we have for this pair.

Kimi K2-Thinking-0905

View details

Moonshot AI

Larger context window (262,144 tokens)

Less expensive input tokens

Less expensive output tokens

Has open weights

Higher GPQA score (84.5% vs 48.0%)

Detailed Comparison

AI Model Comparison Table
Feature	GPT-4 Turbo	Kimi K2-Thinking-0905

FAQ

Common questions about GPT-4 Turbo vs Kimi K2-Thinking-0905.

Which is better, GPT-4 Turbo or Kimi K2-Thinking-0905?

Kimi K2-Thinking-0905 significantly outperforms across most benchmarks. GPT-4 Turbo is made by OpenAI and Kimi K2-Thinking-0905 is made by Moonshot AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does GPT-4 Turbo compare to Kimi K2-Thinking-0905 in benchmarks?

GPT-4 Turbo scores MGSM: 88.5%, HumanEval: 87.1%, MMLU: 86.5%, DROP: 86.0%, MATH: 72.6%. Kimi K2-Thinking-0905 scores AIME 2025: 100.0%, HMMT 2025: 97.5%, MMLU-Redux: 94.4%, FRAMES: 87.0%, MMLU-Pro: 84.6%.

Is GPT-4 Turbo cheaper than Kimi K2-Thinking-0905?

Kimi K2-Thinking-0905 is 21.3x cheaper for input tokens. GPT-4 Turbo costs $10.00/M input and $30.00/M output via azure. Kimi K2-Thinking-0905 costs $0.47/M input and $2.00/M output via deepinfra.

What are the context window sizes for GPT-4 Turbo and Kimi K2-Thinking-0905?

GPT-4 Turbo supports 128K tokens and Kimi K2-Thinking-0905 supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-4 Turbo and Kimi K2-Thinking-0905?

Key differences include context window (128K vs 262K), input pricing ($10.00 vs $0.47/M), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-4 Turbo and Kimi K2-Thinking-0905?

GPT-4 Turbo is developed by OpenAI and Kimi K2-Thinking-0905 is developed by Moonshot AI.