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 | 6B |
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 | 8k |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.40International (Singapore) | — |
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. | $1.60 | — |
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. | $0.32Alibaba | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.28Alibaba | — |
| $128Alibaba | — | |
| These models have no shared benchmark scores. | ||
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. | 77.7% | — |
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. | 89.6% | — |
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. | — | 35.9% |
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. | 34.7% | — |
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. | 73.3% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Jun 1 2026 | Jul 25 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3.7-PlusvsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Qwen3.7-PlusvsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraQwen3.7-PlusvsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenQwen3.7-PlusvsMuse EmberCodeGeeX2-6BvsMuse EmberQwen3.7-PlusvsGrok 4.7CodeGeeX2-6BvsGrok 4.7Qwen3.7-PlusvsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.7-Plus and CodeGeeX2-6B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Qwen3.7-Plus has a verified first-party price for an available API: $0.40 per million input tokens and $1.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for CodeGeeX2-6B. The listed Qwen3.7-Plus rates use the “International (Singapore)” pricing scope. CodeGeeX2-6B shipped 1042 days before Qwen3.7-Plus, so benchmark comparisons should account for the intervening progress.
Qwen3.7-Plus has 397B parameters, while CodeGeeX2-6B has 6B. Context windows are 1M (Qwen3.7-Plus) vs 8k (CodeGeeX2-6B). Qwen3.7-Plus is closed, while CodeGeeX2-6B is open weight.
Direct benchmark comparisons are unavailable — Qwen3.7-Plus and CodeGeeX2-6B don't publish scores on any of the same benchmarks.