Gemini 3.5 FlashvsQwen3.5
Gemini 3.5 Flash | Qwen3.5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 397B |
Context window | — | 1M |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 20% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 14.1% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 54.2% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 60.5% | — |
Agentic coding SWE-Bench ProCan 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. | 55.1% | — |
Coding SWE-Bench VerifiedReal 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. | — | 76.4% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 69.3% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 48.8% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 49.8% | — |
Agentic coding DeepSWE 1.1Artificial 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. | 37% | — |
ML engineering MLE-BenchCan the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | 49.7% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 76.2% | — |
Agentic terminal coding Terminal-Bench 2.0Can 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. | — | 52.5% |
Multi-step tool use MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 83.6% | — |
General tool use ToolathlonTests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 56.5% | — |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 58% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 69% |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity'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. | 40.2%Best | 28.7% |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 72.1% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 88.4% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 78.4%Best | 62.2% |
Agentic financial analysis Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 57.9% | — |
Knowledge work GDPval-AAMeasures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1656 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1349 | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 84.2%Best | 80.8% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 83.6%Best | 79% |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 85% |
Spatial reasoning Blueprint-Bench 2Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 33.6% | — |
Long context MRCR v2 (8-needle) · 128k averageTests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 77.3% | — |
Long context MRCR v2 (8-needle) · 1M pointwiseTests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | 26.6% | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1476 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1492 | — |
| Overview | ||
| Company | Qwen | |
| Release date | May 19 2026 | Feb 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: Gemini 3.5 Flash or Qwen3.5?
Gemini 3.5 Flash leads Qwen3.5 on 4 of the 4 benchmarks they both report (Humanity's Last Exam, OSWorld-Verified, CharXiv Reasoning, MMMU-Pro). Qwen3.5 shipped 92 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.
Gemini 3.5 Flash is proprietary, while Qwen3.5 is open weight.
On Humanity's Last Exam · no tools, Gemini 3.5 Flash leads at 40.2% vs Qwen3.5 at 28.7%. On OSWorld-Verified, Gemini 3.5 Flash leads at 78.4% vs Qwen3.5 at 62.2%. On CharXiv Reasoning, Gemini 3.5 Flash leads at 84.2% vs Qwen3.5 at 80.8%. On MMMU-Pro, Gemini 3.5 Flash leads at 83.6% vs Qwen3.5 at 79%.
Frequently asked questions
Gemini 3.5 Flash was released by Google on May 19 2026.
Qwen3.5 was released by Qwen on Feb 16 2026.
Gemini 3.5 Flash leads on Humanity's Last Exam · no tools — Gemini 3.5 Flash 40.2% vs Qwen3.5 28.7%.
Gemini 3.5 Flash is a proprietary model released by Google. Qwen3.5 is an open weight model released by Qwen.
Other comparisons
Gemini 3.5 FlashvsClaude Opus 5Qwen3.5vsClaude Opus 5Gemini 3.5 FlashvsGPT-5.6 SolQwen3.5vsGPT-5.6 SolGemini 3.5 FlashvsMuse Spark 1.1Qwen3.5vsMuse Spark 1.1Gemini 3.5 FlashvsGrok 4.5Qwen3.5vsGrok 4.5Gemini 3.5 FlashvsDeepSeek-V4-Flash-0731Qwen3.5vsDeepSeek-V4-Flash-0731Gemini 3.5 FlashvsMistral Medium 3.5Qwen3.5vsMistral Medium 3.5