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. | 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 | ||
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 87.1% | 72% |
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. | 50.7% | — |
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. | 76.8% | — |
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. | 73% | — |
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% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 85.7% |
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. | 50.8% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 60.6% | — |
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. | 30.1% | — |
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. | 50.2% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 73% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 96.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87.6% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 86.2% |
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. | 63.3% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | — | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 63.2% |
| Overview | ||
| Company | Moonshot AI | SpaceXSI |
| Release date | Jan 27 2026 | Aug 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2.5vsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Kimi K2.5vsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraKimi K2.5vsGemini 4 HydrogenGrok‑2 minivsGemini 4 HydrogenKimi K2.5vsMuse EmberGrok‑2 minivsMuse EmberKimi K2.5vsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Kimi K2.5vsMistral Large 4Grok‑2 minivsMistral Large 4Frequently asked questions
Kimi K2.5 leads Grok‑2 mini on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 mini shipped 532 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 is open weight, while Grok‑2 mini is closed.
On MMLU-Pro, Kimi K2.5 leads at 87.1% vs Grok‑2 mini at 72%.