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. | 27B/35B/122B | 35B |
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. | 256k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.375International (Singapore) |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.25 |
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. | — | $0.05Darkbloom |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.70Darkbloom |
| — | $45.00Darkbloom · fp4 | |
| 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. | 72% | 73.4% |
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. | 78.9% | 80.4% |
Terminal-Bench 2.0Agentic terminal coding — Can 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. | 49.4% | 51.5% |
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. | 25.3% | 21.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.6% | 86% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 86.7% | 85.2% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 77.2% | 78% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 76.9% | 75.3% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 83.9% | 81.7% |
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. | — | 49.5% |
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. | — | 67.2% |
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. | — | 29.4% |
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. | — | 62.8% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 93.4% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 63.8% | — |
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. | 47.5% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 92.7% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 76.1% | — |
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. | 58% | — |
| Overview | ||
| Company | Qwen | Qwen |
| Release date | Feb 24 2026 | Apr 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3.5 MediumvsClaude Fable 5.2Qwen3.6vsClaude Fable 5.2Qwen3.5 MediumvsGPT-6.2 AstraQwen3.6vsGPT-6.2 AstraQwen3.5 MediumvsGemini 4 NeonQwen3.6vsGemini 4 NeonQwen3.5 MediumvsMuse EmberQwen3.6vsMuse EmberQwen3.5 MediumvsGrok 4.7Qwen3.6vsGrok 4.7Qwen3.5 MediumvsDeepSeek-V4.1-Flash-1017Qwen3.6vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.5 Medium leads Qwen3.6 on 5 of the 9 benchmarks they both report. Only Qwen3.6 has a verified first-party price for an available API: $0.375 per million input tokens and $2.25 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. The listed Qwen3.6 rates use the “International (Singapore)” pricing scope. Qwen3.5 Medium shipped 51 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.
Qwen3.5 Medium has 27B/35B/122B parameters, while Qwen3.6 has 35B. Context windows are 256k (Qwen3.5 Medium) vs 256k (Qwen3.6).
On SWE-Bench Verified, Qwen3.6 leads at 73.4% vs Qwen3.5 Medium at 72%. On LiveCodeBench, Qwen3.6 leads at 80.4% vs Qwen3.5 Medium at 78.9%. On Terminal-Bench 2.0, Qwen3.6 leads at 51.5% vs Qwen3.5 Medium at 49.4%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs Qwen3.6 at 21.4%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Qwen3.6 at 86%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs Qwen3.6 at 85.2%. On CharXiv Reasoning, Qwen3.6 leads at 78% vs Qwen3.5 Medium at 77.2%. On MMMU-Pro, Qwen3.5 Medium leads at 76.9% vs Qwen3.6 at 75.3%. On MMMU, Qwen3.5 Medium leads at 83.9% vs Qwen3.6 at 81.7%.