# Kimi K3

Kimi K3 is an AI model released by Moonshot AI on Jul 16 2026. It has 2.8T parameters, a 1M context window and open weight. Tracked results include 67.5% on DeepSWE 1.0, 74% on BullshitBench v2 and 93.5% on GPQA Diamond.

## Facts

| Field | Value |
| --- | --- |
| Model | Kimi K3 |
| Developer | Moonshot AI |
| Release date | Thursday, Jul 16 2026 |
| Licensing | Open Weight |
| Parameters | 2.8T |
| Context window | 1M |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | Output |
| --- | --- | --- | --- |
| Standard | $3.00 | $0.30 | $15.00 |

Verified August 18, 2026 against the first-party source: https://platform.kimi.ai/docs/pricing/chat-k3.md

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| CheatBench | 70% | [CheatBench](https://cheatbench.ai/), retrieved 2026-09-25 | Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. |
| BullshitBench v2 | 74% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| DeepSWE 1.1 | 69% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. |
| DeepSWE 1.0 | 67.5% | Lab | Artificial 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. |
| Next.js Evals | 84% | [Next.js Evals](https://nextjs.org/evals) | Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. |
| Supabase Evals (with skills) | 87% | [Supabase Evals](https://supabase.com/evals) | Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. |
| Supabase Evals (no skills) | 84.1% | [Supabase Evals](https://supabase.com/evals) | The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. |
| Terminal-Bench 2.1 | 88.3% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. |
| MCP Atlas | 84.2% | Lab | Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. |
| JobBench | 52.9% | Lab | Tests 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. |
| Toolathlon-Verified | 73.2% | Lab | Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. |
| BrowseComp | 91.2% | Lab | Can the AI browse the web and track down hard-to-find answers? Higher is better. |
| Humanity's Last Exam (no tools) | 43.5% | Lab | Humanity'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. |
| Humanity's Last Exam (with tools) | 56% | Lab | Humanity'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. |
| ARC-AGI-2 | 60.4% | [BenchLM](https://benchlm.ai), retrieved 2026-09-28 | Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. |
| GPQA Diamond | 93.5% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| GDPval-AA v2 | 1668 | Lab | economically valuable knowledge work (v2, re-based Elo) |
| CharXiv Reasoning | 84.8% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 81.6% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |
| threejseval | 1527 | [threejseval](https://threejseval.com/ranking) | Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. |

## About Kimi K3

Kimi K3, released July 16, 2026, was Moonshot AI's biggest swing yet: a 2.8-trillion-parameter mixture-of-experts model — billed as the world's first open 3T-class release — activating 16 of 896 experts per token, with a 1M-token context window and native vision built on the lab's Kimi Delta Attention architecture. At launch it scored 93.5% on GPQA Diamond, the strongest open-weight result on that benchmark published at the time, alongside 88.3% on Terminal-Bench 2.1.

Agentic work was the headline: 91.2% on BrowseComp — the best published score on this tracker at release — plus 56.0% on Humanity's Last Exam with tools and 84.2% on MCP Atlas. Moonshot's own framing placed K3 just behind Claude Fable 5 and GPT-5.6 Sol overall while undercutting both sharply on price, and the lab promised full open weights within days of the API launch — the same open-frontier playbook that began with K2 a year earlier, now at nearly triple the scale.

## Questions and answers

### When was Kimi K3 released?

Kimi K3 was released by Moonshot AI on Thursday, Jul 16 2026.

### Who made Kimi K3?

Kimi K3 was built by Moonshot AI. Chinese AI company building the Kimi family of models. Founded in 2023, known for long-context and efficient MoE architectures.

### How much does Kimi K3 cost?

Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens through the Moonshot AI API. Cached input is $0.30 per million tokens. Rates are pay-as-you-go API prices verified against Moonshot AI's published pricing on August 18, 2026.

### What benchmark scores did Kimi K3 get?

Kimi K3 reports 20 tracked benchmark scores — CheatBench: 70%; BullshitBench v2: 74%; DeepSWE 1.1: 69%; DeepSWE 1.0: 67.5%; Next.js Evals: 84%; Supabase Evals (with skills): 87%; Supabase Evals (no skills): 84.1%; Terminal-Bench 2.1: 88.3%; MCP Atlas: 84.2%; JobBench: 52.9%; Toolathlon-Verified: 73.2%; BrowseComp: 91.2%; Humanity's Last Exam (no tools): 43.5%; Humanity's Last Exam (with tools): 56%; ARC-AGI-2: 60.4%; GPQA Diamond: 93.5%; GDPval-AA v2: 1668; CharXiv Reasoning: 84.8%; MMMU-Pro: 81.6%; threejseval: 1527. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data. It holds the best score among all models tracked here on DeepSWE 1.0.

### What is the context window of Kimi K3?

Kimi K3 has a context window of 1M. That is the maximum amount of input plus output the model can hold in a single request.

### How many parameters does Kimi K3 have?

Kimi K3 is reported at 2.8T parameters.

### Is Kimi K3 open source?

Partly. Kimi K3 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Kimi K3?

Moonshot AI's previous tracked release was Kimi K2.7 Code on Jun 12 2026, 34 days earlier. It is the most recent Moonshot AI model tracked on AI Release Tracker.


---

Canonical page: https://aireleasetracker.com/model/moonshot/kimi-k3
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.