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 | 355B |
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 | 128k |
| 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. | — | $0.60 |
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. | — | $2.20 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.11 |
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. | — | $0.60Z.AI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.20Z.AI |
| — | $230Z.ai list price | |
| 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% | 64.2% |
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% | 72.9% |
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% | 79.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 86.7% | 84.6% |
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. | — | 8% |
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% | — |
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 · 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% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 14.4% |
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% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 98.2% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 91% |
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% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 77.2% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 76.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 83.9% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Feb 24 2026 | Jul 28 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3.5 MediumvsClaude Fable 5.2GLM-4.5vsClaude Fable 5.2Qwen3.5 MediumvsGPT-6.2 AstraGLM-4.5vsGPT-6.2 AstraQwen3.5 MediumvsGemini 4 NeonGLM-4.5vsGemini 4 NeonQwen3.5 MediumvsMuse EmberGLM-4.5vsMuse EmberQwen3.5 MediumvsGrok 4.7GLM-4.5vsGrok 4.7Qwen3.5 MediumvsDeepSeek-V4.1-Flash-1017GLM-4.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.5 Medium leads GLM-4.5 on 4 of the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond, MMLU-Pro). Only GLM-4.5 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. GLM-4.5 shipped 211 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.
Qwen3.5 Medium has 27B/35B/122B parameters, while GLM-4.5 has 355B. Context windows are 256k (Qwen3.5 Medium) vs 128k (GLM-4.5).
On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs GLM-4.5 at 64.2%. On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs GLM-4.5 at 72.9%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs GLM-4.5 at 79.1%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs GLM-4.5 at 84.6%.