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. | 0.8B/2B/4B/9B | 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. | — | $1.40 |
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. | — | $4.40 |
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. | — | $0.26 |
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. | — | $0.90Chutes |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.90Chutes |
| — | $325Chutes · fp8 | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 81.7% | 86.2% |
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. | — | 22% |
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. | — | 58.4% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 57% |
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. | — | 42.7% |
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. | 65.6% | — |
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. | — | 63.5% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 91.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 68% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 31% |
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. | — | 52.3% |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 95.3% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 64.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 82.5% | — |
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. | 41.8% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 73% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 70.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 78.4% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Mar 2 2026 | Apr 7 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3.5 SmallvsClaude Fable 5.2GLM-5.1vsClaude Fable 5.2Qwen3.5 SmallvsGPT-6.2 AstraGLM-5.1vsGPT-6.2 AstraQwen3.5 SmallvsGemini 4 NeonGLM-5.1vsGemini 4 NeonQwen3.5 SmallvsMuse EmberGLM-5.1vsMuse EmberQwen3.5 SmallvsGrok 4.7GLM-5.1vsGrok 4.7Qwen3.5 SmallvsDeepSeek-V4.1-Flash-1017GLM-5.1vsDeepSeek-V4.1-Flash-1017Frequently asked questions
GLM-5.1 leads Qwen3.5 Small on 1 of the 1 benchmark they both report (GPQA Diamond). Only GLM-5.1 has a verified first-party price for an available API: $1.40 per million input tokens and $4.40 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Small. Qwen3.5 Small shipped 36 days before GLM-5.1, so benchmark comparisons should account for the intervening progress.
Qwen3.5 Small has 0.8B/2B/4B/9B parameters, while GLM-5.1 has 744B. Context windows are 256k (Qwen3.5 Small) vs 200k (GLM-5.1).
On GPQA Diamond, GLM-5.1 leads at 86.2% vs Qwen3.5 Small at 81.7%.