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 | 80B |
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. | 128k | 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. | $0.57Novita | $0.12Parasail |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.30Novita | $0.80Parasail |
| $229Novita · fp8 | $64.00Parasail · bf16 | |
| 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. | 65.8% | 70.6% |
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. | 10% | — |
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. | — | 44.3% |
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. | — | 62.8% |
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. | — | 36.2% |
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. | 4.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.1% | — |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jul 11 2025 | Feb 3 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K2vsClaude Haiku 5.5Qwen3-Coder-NextvsClaude Haiku 5.5Kimi K2vsGPT-6.1 TerraQwen3-Coder-NextvsGPT-6.1 TerraKimi K2vsGemini 4 CarbonQwen3-Coder-NextvsGemini 4 CarbonKimi K2vsMuse Spark OpenQwen3-Coder-NextvsMuse Spark OpenKimi K2vsGrok 4.7Qwen3-Coder-NextvsGrok 4.7Kimi K2vsDeepSeek-V4.1-Flash-1017Qwen3-Coder-NextvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Coder-Next leads Kimi K2 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Kimi K2 shipped 207 days before Qwen3-Coder-Next, so benchmark comparisons should account for the intervening progress.
Kimi K2 has 1T parameters, while Qwen3-Coder-Next has 80B. Context windows are 128k (Kimi K2) vs 256k (Qwen3-Coder-Next).
On SWE-Bench Verified, Qwen3-Coder-Next leads at 70.6% vs Kimi K2 at 65.8%.