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. | — | 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. | 1M | 256k |
| 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. | 35.1% | 65.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 62.1% | 81.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 76.4% | 82.5% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 70.7% | 78.4% |
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. | 15% | — |
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. | 21.4% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 91.5% |
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% |
| Overview | ||
| Company | Qwen | |
| Release date | Dec 11 2024 | Mar 2 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.0 FlashvsClaude Fable 5.2Qwen3.5 SmallvsClaude Fable 5.2Gemini 2.0 FlashvsGPT-6.2 AstraQwen3.5 SmallvsGPT-6.2 AstraGemini 2.0 FlashvsMuse EmberQwen3.5 SmallvsMuse EmberGemini 2.0 FlashvsGrok 4.7Qwen3.5 SmallvsGrok 4.7Gemini 2.0 FlashvsDeepSeek-V4.1-Flash-1017Qwen3.5 SmallvsDeepSeek-V4.1-Flash-1017Gemini 2.0 FlashvsMistral Large 4Qwen3.5 SmallvsMistral Large 4Frequently asked questions
Qwen3.5 Small leads Gemini 2.0 Flash on 4 of the 4 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro, MMMU). Gemini 2.0 Flash shipped 446 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.0 Flash) vs 256k (Qwen3.5 Small). Gemini 2.0 Flash is closed, while Qwen3.5 Small is open weight.
On LiveCodeBench, Qwen3.5 Small leads at 65.6% vs Gemini 2.0 Flash at 35.1%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Gemini 2.0 Flash at 62.1%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs Gemini 2.0 Flash at 76.4%. On MMMU, Qwen3.5 Small leads at 78.4% vs Gemini 2.0 Flash at 70.7%.