Claude Fable 5vsKimi K2
Claude Fable 5 | Kimi K2 | |
|---|---|---|
| Specifications | ||
Parameters | — | 1T |
Context window | 1M | 128k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 54%Best | 10% |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 80.3% | — |
Coding SWE-Bench VerifiedReal 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. | 95.5%Best | 65.8% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 70.5% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 72.9% | — |
Agentic coding DeepSWE 1.1Artificial 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. | 70% | — |
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. | 66.1% | — |
Next.js coding Next.js EvalsVercel'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. | 92% | — |
Agentic computer work Frontier-Bench v0.1A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | 33.8% | — |
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% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 86.9% | — |
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. | 64.5% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 75.1% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 85% | — |
Agentic legal work Harvey's Legal Agent BenchmarkHarvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better. | 11.25% | — |
Tax questions TaxEval v2A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better. | 76.94% | — |
Medical admin work MedScribeCan the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 88.52% | — |
Knowledge work GDPval-AAMeasures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1932 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1760 | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1509 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1631 | — |
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Jun 9 2026 | Jul 11 2025 |
| Access | Proprietary | Open Weight |
Which is better: Claude Fable 5 or Kimi K2?
Claude Fable 5 leads Kimi K2 on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). Kimi K2 shipped 333 days before Claude Fable 5, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Fable 5) vs 128k (Kimi K2). Claude Fable 5 is proprietary, while Kimi K2 is open weight.
On BullshitBench v2, Claude Fable 5 leads at 54% vs Kimi K2 at 10%. On SWE-Bench Verified, Claude Fable 5 leads at 95.5% vs Kimi K2 at 65.8%.
Frequently asked questions
Claude Fable 5 was released by Anthropic on Jun 9 2026.
Kimi K2 was released by Moonshot AI on Jul 11 2025.
Claude Fable 5 leads on SWE-Bench Verified — Claude Fable 5 95.5% vs Kimi K2 65.8%.
Claude Fable 5 has a 1M context window; Kimi K2 has 128k.
Claude Fable 5 is a proprietary model released by Anthropic. Kimi K2 is an open weight model released by Moonshot AI.
Other comparisons
Claude Fable 5vsGPT-5.6 SolKimi K2vsGPT-5.6 SolClaude Fable 5vsGemini 3.6 FlashKimi K2vsGemini 3.6 FlashClaude Fable 5vsMuse Spark 1.1Kimi K2vsMuse Spark 1.1Claude Fable 5vsGrok 4.5Kimi K2vsGrok 4.5Claude Fable 5vsDeepSeek-V4-ProKimi K2vsDeepSeek-V4-ProClaude Fable 5vsMistral Medium 3.5Kimi K2vsMistral Medium 3.5