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 | 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 | 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 |
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. | — | $0.32DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.40DeepInfra |
| — | $168DeepInfra · 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. | 77.2% | 73.8% |
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. | 71.3% | 66.7% |
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. | 83.9% | 84.9% |
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. | 59.3% | 41% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87.8% | 85.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 86.2% | 84.3% |
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. | 36.2% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 52% |
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. | 24% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 24.8% |
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. | — | 42.8% |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | 94.1% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 95.7% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 78.4% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 75.8% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 82.9% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Apr 22 2026 | Dec 22 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3.6-27BvsClaude Fable 5.2GLM-4.7vsClaude Fable 5.2Qwen3.6-27BvsGPT-6.2 AstraGLM-4.7vsGPT-6.2 AstraQwen3.6-27BvsGemini 4 NeonGLM-4.7vsGemini 4 NeonQwen3.6-27BvsMuse EmberGLM-4.7vsMuse EmberQwen3.6-27BvsGrok 4.7GLM-4.7vsGrok 4.7Qwen3.6-27BvsDeepSeek-V4.1-Flash-1017GLM-4.7vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.6-27B leads GLM-4.7 on 5 of the 6 benchmarks they both report. Only GLM-4.7 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 Qwen3.6-27B. GLM-4.7 shipped 121 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.
Qwen3.6-27B has 27B parameters, while GLM-4.7 has 355B. Context windows are 256k (Qwen3.6-27B) vs 200k (GLM-4.7).
On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs GLM-4.7 at 73.8%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs GLM-4.7 at 66.7%. On LiveCodeBench, GLM-4.7 leads at 84.9% vs Qwen3.6-27B at 83.9%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs GLM-4.7 at 41%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs GLM-4.7 at 85.7%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs GLM-4.7 at 84.3%.