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 | 0.8B/2B/4B/9B |
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 | 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. | $0.072DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.88DeepInfra | — |
| $73.00DeepInfra · fp8 | — | |
| Benchmarks | ||
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. | 56.6% | 65.6% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 87.6% | 91.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 72.9% | 81.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 80.6% | 82.5% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 64.5% |
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 | Qwen |
| Release date | Sep 11 2025 | Mar 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3-NextvsClaude Fable 5.2Qwen3.5 SmallvsClaude Fable 5.2Qwen3-NextvsGPT-6.2 AstraQwen3.5 SmallvsGPT-6.2 AstraQwen3-NextvsGemini 4 NeonQwen3.5 SmallvsGemini 4 NeonQwen3-NextvsMuse EmberQwen3.5 SmallvsMuse EmberQwen3-NextvsGrok 4.7Qwen3.5 SmallvsGrok 4.7Qwen3-NextvsDeepSeek-V4.1-Flash-1017Qwen3.5 SmallvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.5 Small leads Qwen3-Next on 4 of the 4 benchmarks they both report (LiveCodeBench, IFEval, GPQA Diamond, MMLU-Pro). Qwen3-Next shipped 172 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.
Qwen3-Next has 80B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 256k (Qwen3-Next) vs 256k (Qwen3.5 Small).
On LiveCodeBench, Qwen3.5 Small leads at 65.6% vs Qwen3-Next at 56.6%. On IFEval, Qwen3.5 Small leads at 91.5% vs Qwen3-Next at 87.6%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Qwen3-Next at 72.9%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs Qwen3-Next at 80.6%.