Special edition · one baseline, many numbers · 1,342,992 baseline numbers from 106,622 papers
3DGS on Mip-NeRF360 is reported by 56 papers, from 16.06 to 29.04 PSNR. "We beat 3DGS by 2 points" depends on whose number you started from.
Results tables compare a new method with baselines, and the baseline numbers are usually copied from another paper or rerun by the authors. scime atlas read the results tables of 106,622 papers (ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV, ECCV, TPAMI, IJCV, JMLR, 2016–2026) and found 1,342,992 baseline numbers. Grouped by method, benchmark and metric, 18,843 baselines appear in two or more papers; 600 appear in 5 or more.
For 328 of those 600 the highest and lowest reported numbers are more than 5% apart (measured against the median), and for 175 even the middle half of the papers is that far apart. Some of it is real: different training budgets, splits, resolutions or reimplementations. Some is copying from different sources, and a little is misreading. Either way, the number a paper calls "the baseline" is a choice.
3DGS on Mip-NeRF360 (PSNR)
56 papers report 16.06 to 29.04, median 27.46
3DGS on Deep Blending (PSNR)
43 papers report 28.04 to 30.07, median 29.46
GCN on Cora (accuracy)
42 papers report 74.82 to 87.78, median 82.03
GCN on Pubmed (accuracy)
38 papers report 75.61 to 88.9, median 79
3DGS on Tanks&Temples (PSNR)
37 papers report 22.22 to 25.54, median 23.67
GCN on Citeseer (accuracy)
30 papers report 67.42 to 81.39, median 70.3
Each dot is one paper's number. Every line runs from 25% below to 25% above the median (the tick in the middle); numbers further out sit at the ends. The shaded band holds the middle half of the papers.
AI-assisted. The numbers were read by AI from each paper's results tables and not checked by hand; a few are misread, and a benchmark name can hide different splits or settings. Open the papers before you quote a number.
Every approach page on the research map lists the baseline numbers that disagree inside it, with the papers on both ends.
The baselines that appear in the most results tables, each with every paper's number. Some agree to the decimal (the Swin and DeiT numbers on ImageNet are mostly copied from the original papers); others spread over many points.
Lines run from 25% below to 25% above each median; numbers further out sit at the ends.
| Baseline · benchmark · metric | Papers | Each paper's number | Reported | Topic |
|---|---|---|---|---|
| 3DGS Mip-NeRF360 · PSNR · higher is better | 56 | 16.06 – 29.04 median 27.46 | Gaussian splatting | |
| 3DGS Deep Blending · PSNR · higher is better | 43 | 28.04 – 30.07 median 29.46 | Gaussian splatting | |
| GCN Cora · accuracy · higher is better | 42 | 74.82 – 87.78 median 82.03 | GNN architectures | |
| GCN Pubmed · accuracy · higher is better | 38 | 75.61 – 88.9 median 79 | GNN architectures | |
| 3DGS Tanks&Temples · PSNR · higher is better | 37 | 22.22 – 25.54 median 23.67 | Gaussian splatting | |
| DeiT-S ImageNet-1k val · top-1 accuracy (%) · higher is better | 35 | 79.8 – 81.2 median 79.8 | Attention and transformers | |
| Swin-T ImageNet-1K val · top-1 accuracy · higher is better | 34 | 81.18 – 81.3 median 81.3 | Attention and transformers | |
| GCN Citeseer · accuracy · higher is better | 30 | 67.42 – 81.39 median 70.3 | GNN architectures | |
| DDPM CIFAR-10 · FID · lower is better | 29 | 1.97 – 7.76 median 3.17 | Fast diffusion sampling | |
| GAT Cora · accuracy · higher is better | 28 | 76.24 – 88.3 median 83 | GNN architectures | |
| DeiT-B ImageNet-1k val · top-1 accuracy · higher is better | 26 | 81.8 – 83.4 median 81.8 | Attention and transformers | |
| GAT Citeseer · accuracy · higher is better | 26 | 68.4 – 80.52 median 72.5 | GNN architectures | |
| MAML miniImageNet 5-way 5-shot · accuracy · higher is better | 26 | 51.95 – 70.02 median 63.11 | Zero-/few-shot and meta-learning | |
| 3DGS Mip-NeRF360 · LPIPS · lower is better | 23 | 0.182 – 0.389 median 0.216 | Gaussian splatting | |
| Qwen2.5-VL-7B MMStar · accuracy · higher is better | 21 | 48.53 – 67.1 median 62.1 | Multimodal LLMs | |
| ERM Waterbirds · worst-group accuracy · higher is better | 20 | 38.9 – 85.78 median 69.1 | Recognition and long-tail | |
| MAE ADE20K · mIoU · higher is better | 20 | 26.54 – 51.5 median 48.1 | Self-supervised and contrastive | |
| Swin-S ImageNet-1K val · top-1 accuracy · higher is better | 20 | 83 – 83.3 median 83 | Attention and transformers | |
| MAML miniImageNet 5-way 1-shot · accuracy · higher is better | 20 | 32.93 – 54.73 median 48.7 | Zero-/few-shot and meta-learning | |
| GroupDRO Waterbirds · worst-group accuracy · higher is better | 19 | 63.6 – 93.23 median 90.7 | Recognition and long-tail | |
| Swin-B ImageNet-1K val · top-1 accuracy (%) · higher is better | 19 | 83.3 – 83.5 median 83.5 | Attention and transformers | |
| WL NCI1 · accuracy · higher is better | 19 | 79.98 – 85.8 median 84.46 | GNN architectures | |
| LLaVA-1.5 MME · score · higher is better | 18 | 1434 – 1859 median 1511 | Multimodal LLMs | |
| GIN NCI1 · accuracy · higher is better | 18 | 75.04 – 82.75 median 80 | GNN architectures | |
| CenterPoint nuScenes test · mAP · higher is better | 18 | 49.54 – 60.3 median 58 | 3D detection and driving | |
| WGAN-GP CIFAR-10 · FID · lower is better | 18 | 18.21 – 72.23 median 32.75 | GANs | |
| OpenVLA-OFT LIBERO-Long · success rate (%) · higher is better | 18 | 90.7 – 95.8 median 94.5 | Robot action and navigation | |
| GAT Pubmed · accuracy · higher is better | 17 | 77.2 – 87.39 median 79 | GNN architectures | |
| T2M-GPT HumanML3D test · FID · lower is better | 17 | 0.116 – 0.141 median 0.116 | Video generation | |
| Qwen2.5-VL-7B MathVista · accuracy · higher is better | 17 | 61.4 – 70.2 median 68.2 | Multimodal LLMs | |
| KPConv S3DIS Area 5 · mIoU · higher is better | 17 | 64.6 – 67.1 median 67.1 | Point cloud classification | |
| ResNet-50 ImageNet · top-1 accuracy · higher is better | 17 | 67.3 – 78.6 median 76.13 | RNNs and normalization | |
| DiffusionDrive NAVSIM navtest · PDMS · higher is better | 16 | 88.1 – 88.1 median 88.1 | Robot action and navigation | |
| Scaffold-GS Deep Blending · PSNR · higher is better | 16 | 29.98 – 30.37 median 30.21 | Gaussian splatting | |
| DeiT-B ImageNet-1K · Top-1 accuracy · higher is better | 16 | 81.73 – 83.36 median 81.8 | Attention and transformers | |
| DUET R2R Val Unseen · SR · higher is better | 16 | 70.2 – 72 median 72 | Robot action and navigation | |
| Qwen2.5-VL-7B MathVision · accuracy · higher is better | 16 | 24 – 26.4 median 25.15 | Multimodal LLMs | |
| ResNet-50 ImageNet-1k val · top-1 accuracy · higher is better | 16 | 75.3 – 80.83 median 76.2 | CNN features | |
| VAE CelebA · FID · lower is better | 16 | 38.76 – 132.8 median 63 | Variational and generative sampling | |
| GIN MUTAG · accuracy · higher is better | 16 | 74 – 93.5 median 89.4 | GNN architectures |
Free for signed-in readers
Two more pages: the 30 baselines whose numbers are furthest apart, with the papers at both ends, and every research area side by side. Sign in with a free scime account to keep reading.
Already signed in? Reload this page. Accounts are free; we only use your email to sign you in and, if you agree, to tell you about new editions.
Numbers. For 106,622 papers an AI model read the full text and recorded each row of the results tables: setting (benchmark and split), metric, method, whether it is the paper's own method or a baseline, and the number. These were not checked by hand.
Grouping. Baseline rows are grouped by method, setting and metric with letters, digits and case folded (as on the topic pages), so "Mip-NeRF 360" and "MipNeRF360" are one benchmark but different splits named the same way are not told apart. A paper that reports the same baseline twice with different numbers is left out of that group; numbers on another scale (a fraction among percentages) and far outliers are dropped, as on the topic pages. "More than 5% apart": highest minus lowest, divided by the median.
Corrections: contact@latenticlabs.com. Not affiliated with or endorsed by any of the conferences or journals.
← All editions · © 2026 Latentic Labs