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. | 284B | 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. | $0.0434Wafer | $0.60Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.1333Baidu | $2.50Novita |
| $15.54Baidu · fp8 | $245Novita · 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. | 79% | 71.3% |
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. | 39% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 82.7% | — |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 70.3% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 73.2% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 76.7% | — |
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. | 34.8% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 61.4% | — |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 25.1% | — |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | Jul 31 2026 | Nov 6 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Flash-0731vsClaude Haiku 5.5Kimi K2 ThinkingvsClaude Haiku 5.5DeepSeek-V4-Flash-0731vsGPT-6.1 TerraKimi K2 ThinkingvsGPT-6.1 TerraDeepSeek-V4-Flash-0731vsGemini 4 CarbonKimi K2 ThinkingvsGemini 4 CarbonDeepSeek-V4-Flash-0731vsMuse Spark OpenKimi K2 ThinkingvsMuse Spark OpenDeepSeek-V4-Flash-0731vsGrok 4.7Kimi K2 ThinkingvsGrok 4.7DeepSeek-V4-Flash-0731vsMistral Large 4Kimi K2 ThinkingvsMistral Large 4Frequently asked questions
DeepSeek-V4-Flash-0731 leads Kimi K2 Thinking on 1 of the 1 benchmark they both report (SWE-Bench Verified). Kimi K2 Thinking shipped 267 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash-0731 has 284B parameters, while Kimi K2 Thinking has 1T. Context windows are 1M (DeepSeek-V4-Flash-0731) vs 256k (Kimi K2 Thinking).
On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs Kimi K2 Thinking at 71.3%.