Model Comparison

Claude 3.7 Sonnet vs Kimi K2-Instruct-0905Which is better in 2026?

Claude 3.7 Sonnet significantly outperforms across most benchmarks.

Verdict: Claude 3.7 Sonnet vs Kimi K2-Instruct-0905 — which is better?

Claude 3.7 Sonnet (by Anthropic) and Kimi K2-Instruct-0905 (by Moonshot AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Claude 3.7 Sonnet outperforms in 6 benchmarks (AIME 2024, AIME 2025, GPQA, IFEval, SWE-Bench Verified, Terminal-Bench), while Kimi K2-Instruct-0905 is better at 1 benchmark (MATH-500). Claude 3.7 Sonnet significantly outperforms across most benchmarks.

Choose Claude 3.7 Sonnet if…

  • you want the strongest raw capability — it leads on 6 of 7 shared benchmarks

Choose Kimi K2-Instruct-0905 if…

  • you want the most recent training data — it shipped Sep 2025
  • you need open weights you can self-host or fine-tune
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

7 benchmarks

Claude 3.7 Sonnet outperforms in 6 benchmarks (AIME 2024, AIME 2025, GPQA, IFEval, SWE-Bench Verified, Terminal-Bench), while Kimi K2-Instruct-0905 is better at 1 benchmark (MATH-500).

Claude 3.7 Sonnet significantly outperforms across most benchmarks.

Sun Jun 07 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
Sun Jun 07 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Claude 3.7 Sonnet supports multimodal inputs, whereas Kimi K2-Instruct-0905 does not.

Claude 3.7 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3.7 Sonnet

Text
Images
Audio
Video

Kimi K2-Instruct-0905

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.7 Sonnet 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.

Claude 3.7 Sonnet

Proprietary

Closed source

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while Kimi K2-Instruct-0905 was released on 2025-09-05.

Kimi K2-Instruct-0905 is 6 months newer than Claude 3.7 Sonnet.

Claude 3.7 Sonnet

Feb 24, 2025

1.3 years ago

Kimi K2-Instruct-0905

Sep 5, 2025

9 months ago

6mo newer

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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Anthropic
Larger context window (200,000 tokens)
Supports multimodal inputs
Higher AIME 2024 score (80.0% vs 69.6%)
Higher AIME 2025 score (54.8% vs 49.5%)
Higher GPQA score (84.8% vs 75.1%)
Higher IFEval score (93.2% vs 89.8%)
Higher SWE-Bench Verified score (70.3% vs 65.8%)
Higher Terminal-Bench score (35.2% vs 25.0%)
Moonshot AI
Has open weights
Higher MATH-500 score (97.4% vs 96.2%)
AnthropicClaude 3.7 Sonnet
Moonshot AIKimi K2-Instruct-0905
Compare in Playground

Detailed Comparison

AI Model Comparison Table
Feature
Anthropic
Claude 3.7 Sonnet
Moonshot AI
Kimi K2-Instruct-0905

FAQ

Common questions about Claude 3.7 Sonnet vs Kimi K2-Instruct-0905.

Which is better, Claude 3.7 Sonnet or Kimi K2-Instruct-0905?

Claude 3.7 Sonnet significantly outperforms across most benchmarks. Claude 3.7 Sonnet is made by Anthropic 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.

How does Claude 3.7 Sonnet compare to Kimi K2-Instruct-0905 in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. Kimi K2-Instruct-0905 scores MATH-500: 97.4%, MMLU-Redux: 92.7%, IFEval: 89.8%, AutoLogi: 89.5%, MMLU: 89.5%.

What are the context window sizes for Claude 3.7 Sonnet and Kimi K2-Instruct-0905?

Claude 3.7 Sonnet supports 200K 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.

What are the main differences between Claude 3.7 Sonnet and Kimi K2-Instruct-0905?

Key differences include multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and Kimi K2-Instruct-0905?

Claude 3.7 Sonnet is developed by Anthropic and Kimi K2-Instruct-0905 is developed by Moonshot AI.

Related comparisons