# Zero-shot Classification on ImageNet 1k V2 R A (test) Source: [Zero-shot Classification on ImageNet 1k V2 R A (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:54.184Z Evaluation of Zero-shot Classification performance on the ImageNet 1k V2, R, and A variants (test split). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | zero-shot classification | | Dataset (including any stated split) | ImageNet 1k V2 R A (test) | | Metric | Top-1 Acc (Test) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Top-1 Acc (Test)](): Higher is better; unit: PERCENT. - [Top-1 Acc (V2)](): Higher is better; unit: PERCENT. - [Top-1 Acc (R)](): Higher is better; unit: PERCENT. - [Top-1 Acc (A)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc (Test) | Result date | Report paper | | --- | --- | --- | --- | | COCA | 86.3 | Not recorded | 68fa6cb31e209131cea35558 | | BASIC | 85.7 | Not recorded | 68fa6cb31e209131cea35558 | | LIT | 84.5 | Not recorded | 68fa6cb31e209131cea35558 | | LIMoE | 84.1 | Not recorded | 68fa6cb31e209131cea35558 | | ALIGN | 76.4 | Not recorded | 68fa6cb31e209131cea35558 | | CLIP | 76.2 | Not recorded | 68fa6cb31e209131cea35558 | ### COCA Top-1 Acc (Test): 86.3. Result ID: 698f2faa3a6c314849f6cdc9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture Image":"ViT-g","Architecture Text":"T-g","Batch size":"65k","Examples seen":"32.8B","Parameters per token":"2.1B","Training objective":"non-contrastive"}. This record does not assert independent reproduction. ### BASIC Top-1 Acc (Test): 85.7. Result ID: 698f2faa3a6c314849f6cdca. [Reporting paper]() Recorded evaluation configuration: {"Architecture Image":"CoAtNet-7","Architecture Text":"T-H","Pretrained":true,"Batch size":"65k","Examples seen":"19.7B PT + 32.8B","Parameters per token":"3B"}. This record does not assert independent reproduction. ### LIT Top-1 Acc (Test): 84.5. Result ID: 698f2faa3a6c314849f6cdcb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture Image":"ViT-g","Architecture Text":"T-g","Pretrained":true,"Batch size":"32k","Examples seen":"25.8B PT + 18.2B","Parameters per token":"2.1B"}. This record does not assert independent reproduction. ### LIMoE Top-1 Acc (Test): 84.1. Result ID: 698f2faa3a6c314849f6cdce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"H/14","Model structure":"One-tower","Batch size":"21k","Examples seen":"23.3B","Parameters per token":"675M"}. This record does not assert independent reproduction. ### ALIGN Top-1 Acc (Test): 76.4. Result ID: 698f2faa3a6c314849f6cdcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture Image":"EffNet-L2","Architecture Text":"T-L","Pretrained Text":true,"Batch size":"16k","Examples seen":"19.8B","Parameters per token":"~ 820M"}. This record does not assert independent reproduction. ### CLIP Top-1 Acc (Test): 76.2. Result ID: 698f2faa3a6c314849f6cdcd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture Image":"ViT-L/14","Architecture Text":"T-B","Uses FixRes":true,"Batch size":"32k","Examples seen":"12.8B","Parameters per token":"~ 400M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.