Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Crash detection | Firmware Targets Various (Heat Press, PLC, Echo Server, Bootstrap, BLE-HCI, GPSTracker, Gateway, L2cap Processor, Snmp Server, CCN-Lite-Relay, SocketCan, Gattupdate) | 76 | May 19, 2026 | ||
| Image Classification | CIFAR-10 | 76 | May 15, 2026 | ||
| Image Compression | Kodak24 512 | 76 | Apr 15, 2026 | ||
| Code Generation | LiveCodeBench | 76 | May 12, 2026 | ||
| Natural Language Understanding | GLUE |
| 76 |
| Jun 29, 2026 |
| Vision-Language Navigation | VLN-CE R2R (val unseen) | 76 | Jun 17, 2026 |
|---|
| Mathematical Reasoning | GSM8K (test) | 76 | Jun 16, 2026 |
|---|
| Intrinsic Dimensionality Estimation | Benchmark Manifolds | 76 | Mar 12, 2026 |
|---|
| Multimodal Logical Reasoning | LogicVista | 76 | Jun 9, 2026 |
|---|
| Node Classification | Flickr | 76 | May 12, 2026 |
|---|
| Digraph construction | Erdős–Rényi model synthetic OICA mixing matrices | 76 | Mar 6, 2026 |
|---|
| Multi-turn Conversation | MT-bench | 76 | May 20, 2026 |
|---|
| Preference Learning | Toy dataset 0% label noise (test) | 76 | Feb 26, 2026 |
|---|
| Remaining Useful Life prediction | C-MAPSS FD004 | 76 | Jun 18, 2026 |
|---|
| Sequential Recommendation | Amazon-Toys | 76 | Jun 17, 2026 |
|---|
| Autonomous Driving Planning | NAVSIM v2 (Navtest) | 76 | Jun 16, 2026 |
|---|
| Image Classification | Tiny-ImageNet | 76 | Mar 10, 2026 |
|---|
| Person Re-identification | CARGO Metadata-free | 76 | Feb 26, 2026 |
|---|
| CRC Surv prognosis prediction | SurGen | 76 | Mar 24, 2026 |
|---|
| Drone-to-Satellite Retrieval | SUES-200 250m | 76 | Apr 3, 2026 |
|---|
| Point Cloud Classification | ModelNet40 v1 (test) | 76 | Feb 26, 2026 |
|---|
| Classification | CB | 76 | Jun 5, 2026 |
|---|
| Mathematical Problem Solving | AIME 2025 | 76 | May 20, 2026 |
|---|
| Forecasting | S&P 500 | 76 | Feb 26, 2026 |
|---|
| Language Modeling | (val) | 76 | May 22, 2026 |
|---|