Gemini 3.0 FlashvsQwen3.8-Flash-Next
Gemini 3.0 Flash | Qwen3.8-Flash-Next | |
|---|---|---|
| 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. | — | 125B |
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. | — | 262k |
| Benchmarks | ||
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% | 62.5% |
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% | 35.9% |
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% | 91.7% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 80.3% | 84.6% |
| BenchmarksPublished by one model only | ||
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% | — |
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. | — | 81% |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 58.7% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 48.1% |
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. | — | 91.9% |
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% | — |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 55.7% |
CoWorkBenchLong-horizon office work — Tests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | — | 73.9% |
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. | — | 73.5% |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 49.4% | — |
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% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 81.3% |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | — | 19.4% |
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% | — |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 24.3% |
Agent's Last Exam · scoreAgentic computer use — The graded score on the same desktop and operating-system tasks in Agent's Last Exam, giving partial credit for progress beyond the strict pass-or-fail result. Higher is better. | — | 51.2% |
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 | — |
LVBenchVideo understanding — Can the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better. | — | 76.6% |
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 | Qwen | |
| Release date | Dec 17 2025 | Aug 26 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Gemini 3.0 FlashvsClaude Opus 5Qwen3.8-Flash-NextvsClaude Opus 5Gemini 3.0 FlashvsGPT-5.6 SolQwen3.8-Flash-NextvsGPT-5.6 SolGemini 3.0 FlashvsMuse GlimmerQwen3.8-Flash-NextvsMuse GlimmerGemini 3.0 FlashvsGrok 4.6Qwen3.8-Flash-NextvsGrok 4.6Gemini 3.0 FlashvsDeepSeek-V4-Pro-0813Qwen3.8-Flash-NextvsDeepSeek-V4-Pro-0813Gemini 3.0 FlashvsMistral Medium 3.5Qwen3.8-Flash-NextvsMistral Medium 3.5
Frequently asked questions
Qwen3.8-Flash-Next leads Gemini 3.0 Flash on 4 of the 4 benchmarks they both report (SWE-Bench Pro, Humanity's Last Exam, GPQA Diamond, CharXiv Reasoning). Gemini 3.0 Flash shipped 252 days before Qwen3.8-Flash-Next, so benchmark comparisons should account for the intervening progress.
Gemini 3.0 Flash is proprietary, while Qwen3.8-Flash-Next is open weight.
On SWE-Bench Pro, Qwen3.8-Flash-Next leads at 62.5% vs Gemini 3.0 Flash at 49.6%. On Humanity's Last Exam · no tools, Qwen3.8-Flash-Next leads at 35.9% vs Gemini 3.0 Flash at 33.7%. On GPQA Diamond, Qwen3.8-Flash-Next leads at 91.7% vs Gemini 3.0 Flash at 90.4%. On CharXiv Reasoning, Qwen3.8-Flash-Next leads at 84.6% vs Gemini 3.0 Flash at 80.3%.
Gemini 3.0 Flash was released by Google on Dec 17 2025.
Qwen3.8-Flash-Next was released by Qwen on Aug 26 2026.
Qwen3.8-Flash-Next leads on SWE-Bench Pro — Gemini 3.0 Flash 49.6% vs Qwen3.8-Flash-Next 62.5%.
Qwen3.8-Flash-Next leads on Humanity's Last Exam · no tools — Gemini 3.0 Flash 33.7% vs Qwen3.8-Flash-Next 35.9%.
Gemini 3.0 Flash is a proprietary model released by Google. Qwen3.8-Flash-Next is an open weight model released by Qwen.