Compare AI models
| 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. | 55% | 62.5% |
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. | 10% | 58.7% |
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. | 17% | 55.7% |
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. | 49.4% | 73.5% |
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. | 50.4% | 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. | 89.5% | 91.7% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.9% | 84.6% |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers 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. | 2.9% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers 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. | 14.3% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers 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. | 16.5% | — |
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. | 77.4% | — |
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% |
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. | 67.3% | — |
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. | 82.2% | — |
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% |
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. | — | 35.9% |
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. | 42.5% | — |
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. | 53.3% | — |
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% |
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% |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | 39.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.4% | — |
| Overview | ||
| Company | Meta | Qwen |
| Release date | Apr 8 2026 | Aug 26 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Muse SparkvsClaude Haiku 5.5Qwen3.8-Flash-NextvsClaude Haiku 5.5Muse SparkvsGPT-6.1 SolQwen3.8-Flash-NextvsGPT-6.1 SolMuse SparkvsGemini 4 ArgonQwen3.8-Flash-NextvsGemini 4 ArgonMuse SparkvsGrok 4.7Qwen3.8-Flash-NextvsGrok 4.7Muse SparkvsDeepSeek-V4.1-FlashQwen3.8-Flash-NextvsDeepSeek-V4.1-FlashMuse SparkvsMistral Large 4Qwen3.8-Flash-NextvsMistral Large 4Frequently asked questions
Qwen3.8-Flash-Next leads Muse Spark on 5 of the 7 benchmarks they both report. Muse Spark shipped 140 days before Qwen3.8-Flash-Next, so benchmark comparisons should account for the intervening progress.
Muse Spark is closed, while Qwen3.8-Flash-Next is open weight.
On SWE-Bench Pro, Qwen3.8-Flash-Next leads at 62.5% vs Muse Spark at 55%. On DeepSWE 1.1, Qwen3.8-Flash-Next leads at 58.7% vs Muse Spark at 10%. On JobBench, Qwen3.8-Flash-Next leads at 55.7% vs Muse Spark at 17%. On Toolathlon-Verified, Qwen3.8-Flash-Next leads at 73.5% vs Muse Spark at 49.4%. On Humanity's Last Exam · with tools, Muse Spark leads at 50.4% vs Qwen3.8-Flash-Next at 35.9%. On GPQA Diamond, Qwen3.8-Flash-Next leads at 91.7% vs Muse Spark at 89.5%. On CharXiv Reasoning, Muse Spark leads at 88.9% vs Qwen3.8-Flash-Next at 84.6%.