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 | 27B/35B/122B |
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 | 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. | 76.8% | 72% |
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% | 78.9% |
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% | 49.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 60.6% | 63.8% |
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% | 25.3% |
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% | 47.5% |
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% | 86.6% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 87.1% | 86.7% |
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% | 58% |
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 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% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 93.4% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 96.1% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 76.1% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 77.2% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 76.9% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 83.9% |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jan 27 2026 | Feb 24 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K2.5vsClaude Fable 5.2Qwen3.5 MediumvsClaude Fable 5.2Kimi K2.5vsGPT-6.2 AstraQwen3.5 MediumvsGPT-6.2 AstraKimi K2.5vsGemini 4 NeonQwen3.5 MediumvsGemini 4 NeonKimi K2.5vsMuse EmberQwen3.5 MediumvsMuse EmberKimi K2.5vsGrok 4.7Qwen3.5 MediumvsGrok 4.7Kimi K2.5vsDeepSeek-V4.1-Flash-1017Qwen3.5 MediumvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2.5 leads Qwen3.5 Medium on 8 of the 9 benchmarks they both report. Kimi K2.5 shipped 28 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 has 1T parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 256k (Kimi K2.5) vs 256k (Qwen3.5 Medium).
On SWE-Bench Verified, Kimi K2.5 leads at 76.8% vs Qwen3.5 Medium at 72%. On LiveCodeBench, Kimi K2.5 leads at 85% vs Qwen3.5 Medium at 78.9%. On Terminal-Bench 2.0, Kimi K2.5 leads at 50.8% vs Qwen3.5 Medium at 49.4%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Kimi K2.5 at 60.6%. On Humanity's Last Exam · no tools, Kimi K2.5 leads at 30.1% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Kimi K2.5 leads at 50.2% vs Qwen3.5 Medium at 47.5%. On GPQA Diamond, Kimi K2.5 leads at 87.6% vs Qwen3.5 Medium at 86.6%. On MMLU-Pro, Kimi K2.5 leads at 87.1% vs Qwen3.5 Medium at 86.7%. On OSWorld-Verified, Kimi K2.5 leads at 63.3% vs Qwen3.5 Medium at 58%.