Gemini 3.0 FlashvsKimi K2
Gemini 3.0 Flash | Kimi K2 | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 1T |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.57Novita |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $2.30Novita |
| 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. | 78% | 65.8% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.4% | 75.1% |
| BenchmarksPublished by one model only | ||
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. | 49.6% | — |
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. | 58% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 62% | — |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 49.4% | — |
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. | 33.7% | — |
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. | 33.6% | — |
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. | 65.1% | — |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 42.6% | — |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1204 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 80.3% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 81.2% | — |
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 0% | — |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 67.2% | — |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | 22.1% | — |
| Overview | ||
| Company | Moonshot AI | |
| Release date | Dec 17 2025 | Jul 11 2025 |
| Access | Proprietary | Open Weight |
Other comparisons
Gemini 3.0 FlashvsClaude Opus 5Kimi K2vsClaude Opus 5Gemini 3.0 FlashvsGPT-5.6 SolKimi K2vsGPT-5.6 SolGemini 3.0 FlashvsMuse GlimmerKimi K2vsMuse GlimmerGemini 3.0 FlashvsGrok 4.6Kimi K2vsGrok 4.6Gemini 3.0 FlashvsDeepSeek-V4-Pro-0813Kimi K2vsDeepSeek-V4-Pro-0813Gemini 3.0 FlashvsMistral Medium 3.5Kimi K2vsMistral Medium 3.5
Frequently asked questions
Gemini 3.0 Flash leads Kimi K2 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Kimi K2 shipped 159 days before Gemini 3.0 Flash, so benchmark comparisons should account for the intervening progress.
Gemini 3.0 Flash is proprietary, while Kimi K2 is open weight.
On SWE-Bench Verified, Gemini 3.0 Flash leads at 78% vs Kimi K2 at 65.8%. On GPQA Diamond, Gemini 3.0 Flash leads at 90.4% vs Kimi K2 at 75.1%.
Gemini 3.0 Flash was released by Google on Dec 17 2025.
Kimi K2 was released by Moonshot AI on Jul 11 2025.
Gemini 3.0 Flash leads on SWE-Bench Verified — Gemini 3.0 Flash 78% vs Kimi K2 65.8%.
Gemini 3.0 Flash leads on GPQA Diamond — Gemini 3.0 Flash 90.4% vs Kimi K2 75.1%.
Gemini 3.0 Flash is a proprietary model released by Google. Kimi K2 is an open weight model released by Moonshot AI.