Canvas & Ratio
Choose your destination platform format
Layout Template
Choose a content structure for your slides
Preset Themes
Typography & Sizing
Brand Kit Customization
AGENCYConfigure brand assets for headers & footers
Outro Slide CTA
Customize your closing call-to-action slide
Background Pattern
Build Your Carousel
Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!
Qwen3 model family overview: full benchmarks for all 8 Qwen3 models in both reasoning and non-reasoning modes Key results: ➤ Qwen3 235B-A22B (Reasoning): The largest Qwen3 model scores 62 on the Artificial Analysis Intelligence Index, becoming the most intelligent open weights model ever. This is very impressive considering the model has only 22B active parameters with 235B total, very few compared to its nearest competitors - NVIDIA’s Llama Nemotron Ultra (dense, 253B) and DeepSeek R1 (37B active, 671B total). One thing Qwen3 is missing is multimodal inputs - Llama 4 and Gemma 3 remain the best open weights models for vision capability. ➤ Qwen3 32B (Reasoning): The largest dense model in the Qwen3 family scores 59 on our Intelligence Index, just behind DeepSeek R1. While 235B-A22B will be both more intelligent and efficient for large scale inference, the 32B is highly compelling for deployments constrained by total memory (including local inference). ➤ Qwen3 30B-A3B (Reasoning): The smaller MoE scores 56 in Intelligence Index, matching the dense 14B. With just 3B active parameters, this model can achieve incredible speed compared to other models of similar intelligence. ➤ Smaller Qwen3 models: 0.6B, 1.7B, 4B and 8B are each independently strong models for their size when used in reasoning mode. These are particularly compelling for on-device use cases. ➤ Non-reasoning performance: We tested all 8 Qwen3 models in non-reasoning mode (using the /no_think soft switch) and overall find that while the models remain effective in non-reasoning mode, they are generally not in a clear leadership position compared to competing non-reasoning models. This may indicate that there continues to be a real cost of a hybrid reasoning approach, as opposed to separate dedicated models. Observations from our detailed analysis of the Qwen3 models: ➤ Consistent uplift from reasoning: we see a significant jump for all models, resulting in interesting consequences like 4B (reasoning) matching the score of 235B-A22B (non-reasoning). We would caution that 235B-A22B is likely to outperform significantly in real world use where reasoning provides a less consistent uplift ➤ Clear demonstration of benefits of MoE models: on the Active Parameters chart, the two MoE models (235B-A22B and 30B-A3B) clearly sit above the trendline formed by the dense models Detailed breakdowns of the full Qwen3 family follow - including token usage.
Intelligence vs. Total Parameters: unlike on the Active Parameters chart above, the MoE models sit below the trendline created by the dense models when we chart Total Parameters. This is because these models are each only activating ~10% of their parameters for each forward pass - and this comes at a cost to intelligence relative to a similar-sized dense model. For inference at scale, the MoE models should be preferred for greater efficiency - but the dense models allow greater intelligence in a smaller total amount of memory.
Comparison to leading models: as detailed above, Qwen3 235B-A22B in reasoning mode is now the leading open weights model in Artificial Analysis Intelligence Index.
Token usage: The Qwen3 models used a similar number of tokens to peer models when used in both their reasoning and non-reasoning modes. We see a clear distinction between the Qwen3 models in reasoning and non-reasoning modes - for example, across all of the evals in Artificial Analysis Intelligence Index, Qwen3 235B-A22B used: ➤ 74M total output tokens (71M reasoning, 3M output) in its default reasoning mode ➤ 7M total output tokens in non-reasoning mode
Compare the entire Qwen 3 family with other leading reasoning and non-reasoning models at: <a target="_blank" href="https://artificialanalysis.ai/?models=gpt-4-1%2Cgpt-4-1-mini%2Co3%2Co4-mini%2Cllama-4-scout%2Cllama-4-maverick%2Cgemini-2-5-flash-reasoning%2Cgemma-3-27b%2Cgemini-2-5-pro%2Cclaude-3-7-sonnet-thinking%2Cdeepseek-r1%2Cdeepseek-v3-0324%2Cgrok-3%2Cgrok-3-mini-reasoning%2Cllama-3-1-nemotron-ultra-253b-v1-reasoning%2Cqwen3-30b-a3b-instruct-reasoning%2Cqwen3-8b-instruct-reasoning%2Cqwen3-0.6b-instruct-reasoning%2Cqwen3-235b-a22b-instruct-reasoning%2Cqwen3-32b-instruct-reasoning%2Cqwen3-4b-instruct-reasoning%2Cqwen3-14b-instruct-reasoning%2Cqwen3-1.7b-instruct-reasoning" color="blue">artificialanalysis.ai/?models=gpt-4-…</a>