Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 1T |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.49AtlasCloud |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.50AtlasCloud |
| — | $223AtlasCloud · int4 | |
| Benchmarks | ||
SWE-Bench VerifiedCoding — 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. | 93.9% | 76.8% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — 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. | 64.7% | 30.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.5% | 87.6% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 79.6% | 63.3% |
BullshitBench v2Nonsense detection — 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. | — | 52% |
SWE-Bench ProAgentic coding — Can 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. | 77.8% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 87.3% | — |
SWE-Bench MultimodalMultimodal coding — Real bug reports that arrive with pictures attached — a screenshot, a mockup, a page rendering wrongly — so the AI has to read the image as well as the code to work out what to fix. Higher is better. | 59% | — |
Next.js EvalsNext.js coding — 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. | — | 18% |
LiveCodeBenchCompetitive coding — 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. | — | 85% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 82% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 60.6% |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.1% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — 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. | 56.8% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 86.1% | — |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | 93.2% | — |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | 80% | — |
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Apr 7 2026 | Jan 27 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Mythos PreviewvsGPT-6.1 TerraKimi K2.5vsGPT-6.1 TerraClaude Mythos PreviewvsGemini 4 CarbonKimi K2.5vsGemini 4 CarbonClaude Mythos PreviewvsMuse EmberKimi K2.5vsMuse EmberClaude Mythos PreviewvsGrok 4.7Kimi K2.5vsGrok 4.7Claude Mythos PreviewvsDeepSeek-V4.1-Flash-1017Kimi K2.5vsDeepSeek-V4.1-Flash-1017Claude Mythos PreviewvsMistral Large 4Kimi K2.5vsMistral Large 4Frequently asked questions
Claude Mythos Preview leads Kimi K2.5 on 4 of the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond, OSWorld-Verified). Kimi K2.5 shipped 70 days before Claude Mythos Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos Preview) vs 256k (Kimi K2.5). Claude Mythos Preview is closed, while Kimi K2.5 is open weight.
On SWE-Bench Verified, Claude Mythos Preview leads at 93.9% vs Kimi K2.5 at 76.8%. On Humanity's Last Exam · with tools, Claude Mythos Preview leads at 64.7% vs Kimi K2.5 at 30.1%. On GPQA Diamond, Claude Mythos Preview leads at 94.5% vs Kimi K2.5 at 87.6%. On OSWorld-Verified, Claude Mythos Preview leads at 79.6% vs Kimi K2.5 at 63.3%.