Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 235B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| 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. | $0.30 | $0.70 |
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. | $2.50 | $2.80 |
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. | $0.03 | — |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.15Google | $0.0482StreamLake |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.25Google | $0.1931StreamLake |
| Benchmarks | ||
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. | 66% | 6% |
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. | 54.2% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 54% | — |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 49% | — |
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. | 74% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1140 | — |
| Overview | ||
| Company | Qwen | |
| Release date | Jul 21 2026 | Apr 29 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 3.5 Flash-LitevsClaude Haiku 5.5Qwen3vsClaude Haiku 5.5Gemini 3.5 Flash-LitevsGPT-6.1 SolQwen3vsGPT-6.1 SolGemini 3.5 Flash-LitevsMuse Spark 1.3Qwen3vsMuse Spark 1.3Gemini 3.5 Flash-LitevsGrok 4.7Qwen3vsGrok 4.7Gemini 3.5 Flash-LitevsDeepSeek-V4.1-FlashQwen3vsDeepSeek-V4.1-FlashGemini 3.5 Flash-LitevsMistral Large 4Qwen3vsMistral Large 4Frequently asked questions
Gemini 3.5 Flash-Lite leads Qwen3 on 1 of the 1 benchmark they both report (BullshitBench v2). Gemini 3.5 Flash-Lite is cheaper on both input and output: $0.30 vs $0.70 per million input tokens, and $2.50 vs $2.80 per million output tokens. Figures are base-tier rates. Qwen3 shipped 448 days before Gemini 3.5 Flash-Lite, so benchmark comparisons should account for the intervening progress.
Gemini 3.5 Flash-Lite is closed, while Qwen3 is open weight.
On BullshitBench v2, Gemini 3.5 Flash-Lite leads at 66% vs Qwen3 at 6%.