# Kimi K2.5

Kimi K2.5 is an AI model released by Moonshot AI on Jan 27 2026. It has 1T parameters, a 256k context window and open weight. Tracked results include 52% on BullshitBench v2, 76.8% on SWE-Bench Verified and 87.6% on GPQA Diamond.

## Facts

| Field | Value |
| --- | --- |
| Model | Kimi K2.5 |
| Developer | Moonshot AI |
| Release date | Tuesday, Jan 27 2026 |
| Licensing | Open Weight |
| Parameters | 1T |
| Context window | 256k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| BullshitBench v2 | 52% | [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. |
| SWE-Bench Verified | 76.8% | Lab | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| Next.js Evals | 16% | [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. |
| LiveCodeBench | 85% | [BenchLM](https://benchlm.ai), retrieved 2026-07-11 | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |
| BrowseComp | 60.6% | [BenchLM](https://benchlm.ai), retrieved 2026-08-31 | Can the AI browse the web and track down hard-to-find answers? Higher is better. |
| Humanity's Last Exam (with tools) | 30.1% | [BenchLM](https://benchlm.ai), retrieved 2026-08-31 | 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. |
| GPQA Diamond | 87.6% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| OSWorld-Verified | 63.3% | [BenchLM](https://benchlm.ai), retrieved 2026-10-12 | Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. |

## About Kimi K2.5

Kimi K2.5 was released in January 2026 as Moonshot AI's multimodal continuation of the K2 line. It added native visual understanding through further training on text and vision material, with applications ranging from interpreting interfaces to building frontend code from visual references. The release supported both immediate responses and longer thinking for tasks requiring more deliberate reasoning.

Moonshot also presented Agent Swarm, a system for splitting complex work into parallel subtasks handled by specialist agents. Results from that setup should be distinguished from ordinary single-agent evaluations. Downloadable model weights gave developers a route to their own deployments, while the hosted Kimi product supplied an additional environment for the broader agent experience.

## Questions and answers

### When was Kimi K2.5 released?

Kimi K2.5 was released by Moonshot AI on Tuesday, Jan 27 2026.

### Who made Kimi K2.5?

Kimi K2.5 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.

### What benchmark scores did Kimi K2.5 get?

Kimi K2.5 reports 8 tracked benchmark scores — BullshitBench v2: 52%; SWE-Bench Verified: 76.8%; Next.js Evals: 16%; LiveCodeBench: 85%; BrowseComp: 60.6%; Humanity's Last Exam (with tools): 30.1%; GPQA Diamond: 87.6%; OSWorld-Verified: 63.3%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Kimi K2.5?

Kimi K2.5 has a context window of 256k. Providers may specify separate input and output token limits.

### How many parameters does Kimi K2.5 have?

Kimi K2.5 is reported at 1T parameters.

### Is Kimi K2.5 open source?

Partly. Kimi K2.5 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 K2.5?

Moonshot AI's previous tracked release was Kimi K2 Thinking on Nov 6 2025, 82 days earlier. It was followed by Kimi K2.6 on Apr 20 2026.


---

Canonical page: https://aireleasetracker.com/model/moonshot/kimi-k2.5
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.