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. | 397B | 744B |
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 | 200k |
| 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 | $1.00 |
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. | $3.60 | $3.20 |
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. | — | $0.20 |
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. | $0.065Alibaba | $0.60GMICloud |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.13Darkbloom | $1.92GMICloud |
| $22.50Darkbloom · fp4 | $216GMICloud · fp8 | |
| Benchmarks | ||
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. | 78% | 28% |
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. | 76.4% | 77.8% |
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. | 69.3% | 73.3% |
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. | 52.5% | 56.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 69% | 75.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.4% | 86% |
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. | 28.7% | — |
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% |
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. | 62.2% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 80.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 79% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 85% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Feb 16 2026 | Feb 11 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Frequently asked questions
GLM-5 leads Qwen3.5 on 4 of the 6 benchmarks they both report. Qwen3.5 is cheaper on input: $0.60 vs $1.00 per million tokens. GLM-5 is cheaper on output: $3.20 vs $3.60 per million tokens. GLM-5 shipped 5 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.
Qwen3.5 has 397B parameters, while GLM-5 has 744B. Context windows are 256k (Qwen3.5) vs 200k (GLM-5).
On BullshitBench v2, Qwen3.5 leads at 78% vs GLM-5 at 28%. On SWE-Bench Verified, GLM-5 leads at 77.8% vs Qwen3.5 at 76.4%. On SWE-Bench Multilingual, GLM-5 leads at 73.3% vs Qwen3.5 at 69.3%. On Terminal-Bench 2.0, GLM-5 leads at 56.2% vs Qwen3.5 at 52.5%. On BrowseComp, GLM-5 leads at 75.9% vs Qwen3.5 at 69%. On GPQA Diamond, Qwen3.5 leads at 88.4% vs GLM-5 at 86%.