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. | — | 80B |
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. | 400k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
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. | — | $0.12Parasail |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.80Parasail |
| — | $64.00Parasail · bf16 | |
| 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. | 45% | — |
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. | — | 44.3% |
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. | — | 70.6% |
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. | — | 62.8% |
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. | 46% | — |
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. | — | 36.2% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Dec 18 2025 | Feb 3 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-5.2-CodexvsClaude Fable 5.2Qwen3-Coder-NextvsClaude Fable 5.2GPT-5.2-CodexvsGemini 4 CarbonQwen3-Coder-NextvsGemini 4 CarbonGPT-5.2-CodexvsMuse EmberQwen3-Coder-NextvsMuse EmberGPT-5.2-CodexvsGrok 4.7Qwen3-Coder-NextvsGrok 4.7GPT-5.2-CodexvsDeepSeek-V4.1-Flash-1017Qwen3-Coder-NextvsDeepSeek-V4.1-Flash-1017GPT-5.2-CodexvsMistral Large 4Qwen3-Coder-NextvsMistral Large 4Frequently asked questions
GPT-5.2-Codex and Qwen3-Coder-Next don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5.2-Codex shipped 47 days before Qwen3-Coder-Next, so benchmark comparisons should account for the intervening progress.
Context windows are 400k (GPT-5.2-Codex) vs 256k (Qwen3-Coder-Next). GPT-5.2-Codex is closed, while Qwen3-Coder-Next is open weight.
Direct benchmark comparisons are unavailable — GPT-5.2-Codex and Qwen3-Coder-Next don't publish scores on any of the same benchmarks.