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. | — | 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. | 1M | 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 | |
| These models have no shared benchmark scores. | ||
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. | 37.8% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 86.6% | — |
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 | 76.3% | — |
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% |
MATHReasoning — accuracy on the original competition mathematics test set | 81.1% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 95.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86.2% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 64.5% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 93.8% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Nov 15 2024 | Apr 7 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen2.5-Turbo (1M)vsClaude Fable 5.2GLM-5.1vsClaude Fable 5.2Qwen2.5-Turbo (1M)vsGPT-6.2 AstraGLM-5.1vsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGemini 4 NeonGLM-5.1vsGemini 4 NeonQwen2.5-Turbo (1M)vsMuse EmberGLM-5.1vsMuse EmberQwen2.5-Turbo (1M)vsGrok 4.7GLM-5.1vsGrok 4.7Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017GLM-5.1vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen2.5-Turbo (1M) and GLM-5.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. 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 Qwen2.5-Turbo (1M). Qwen2.5-Turbo (1M) shipped 508 days before GLM-5.1, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Qwen2.5-Turbo (1M)) vs 200k (GLM-5.1). Qwen2.5-Turbo (1M) is closed, while GLM-5.1 is open weight.
Direct benchmark comparisons are unavailable — Qwen2.5-Turbo (1M) and GLM-5.1 don't publish scores on any of the same benchmarks.