Claude 3 Sonnet vs Kimi K3
Anthropic Claude 3 Sonnet | Moonshot AI Kimi K3 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Mar 4 2024 | Jul 16 2026 |
| Access | Proprietary | Open Weight |
| Specifications | ||
Parameters | — | 2.8T |
Context window | — | 1M |
| Benchmarks | ||
Agentic coding DeepSWE 1.0Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | — | 67.5% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 88.3% |
Multi-step tool use MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 84.2% |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 52.9% |
Personal tool use Toolathlon-VerifiedTests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | — | 73.2% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 91.2% |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 43.5% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 56% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 40.4% | 93.5%Best |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | — | 1668 |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 84.8% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 81.6% |
| Timeline | ||
| Release gap | Claude 3 Sonnet shipped 864 days before Kimi K3 | |
Which is better: Claude 3 Sonnet or Kimi K3?
Kimi K3 leads Claude 3 Sonnet on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Sonnet shipped 864 days before Kimi K3, so benchmark comparisons should account for the intervening progress.
Claude 3 Sonnet is proprietary, while Kimi K3 is open weight.
On GPQA Diamond, Kimi K3 leads at 93.5% vs Claude 3 Sonnet at 40.4%.
Frequently asked questions
Claude 3 Sonnet was released by Anthropic on Mar 4 2024.
Kimi K3 was released by Moonshot AI on Jul 16 2026.
Kimi K3 leads on GPQA Diamond — Claude 3 Sonnet 40.4% vs Kimi K3 93.5%.
Claude 3 Sonnet is a proprietary model released by Anthropic. Kimi K3 is an open weight model released by Moonshot AI.
Other comparisons
Claude 3 Sonnet vs GPT-5.6 SolKimi K3 vs GPT-5.6 SolClaude 3 Sonnet vs Gemini 3.5 FlashKimi K3 vs Gemini 3.5 FlashClaude 3 Sonnet vs Muse Spark 1.1Kimi K3 vs Muse Spark 1.1Claude 3 Sonnet vs Grok 4.5Kimi K3 vs Grok 4.5Claude 3 Sonnet vs DeepSeek-V4-ProKimi K3 vs DeepSeek-V4-ProClaude 3 Sonnet vs Mistral Medium 3.5Kimi K3 vs Mistral Medium 3.5