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 |
|---|---|---|---|---|---|
| ECG Classification | EchoNext (test) | 36 | May 11, 2026 | ||
| Intent Grasping | IntentGrasp Gem Set | 36 | May 11, 2026 | ||
| Regression | Beta-lactamase PEER | 36 | May 11, 2026 | ||
| Binary classification | Neuropeptide (NeuroPID) | 36 | May 11, 2026 | ||
| Maximize sum rate subject to total power constraint | Full Duplex QoS Scenario 08 |
| 36 |
| May 8, 2026 |
| Maximize sum rate with transmit power and interference limits | Cognitive Radio Sum Rate Maximization Scenario 06 | 36 | May 8, 2026 |
|---|
| Forgetting-aware Instruction Tuning | Magicoder Stability and Plasticity suites (test) | 36 | May 8, 2026 |
|---|
| RAG Leakage Attack | ENRON EMAIL | 36 | May 8, 2026 |
|---|
| RAG Leakage Attack | NFCORPUS | 36 | May 8, 2026 |
|---|
| RAG Leakage Attack | SCIFACT | 36 | May 8, 2026 |
|---|
| Science Question Answering | GPQA-Diamond Science N=198 | 36 | May 8, 2026 |
|---|
| Medical Question Answering | HealthBench Medicine N=5,000 (overall) | 36 | May 8, 2026 |
|---|
| Multi-step outcome prediction | RW MIMIC-extract (Latino) | 36 | May 8, 2026 |
|---|
| Multi-step outcome prediction | RW MIMIC-extract (Asian) | 36 | May 8, 2026 |
|---|
| Multi-step-ahead prediction | MIMIC-III (African) | 36 | May 8, 2026 |
|---|
| Continuous Control | MuJoCo HalfCheetah v4 | 36 | May 21, 2026 |
|---|
| Image Regression | RSLC (test) | 36 | May 8, 2026 |
|---|
| Hallucination detection | NQ_Open | 36 | May 6, 2026 |
|---|
| Graph reconstruction | Amz-R | 36 | May 6, 2026 |
|---|
| Graph reconstruction | Chameleon | 36 | May 6, 2026 |
|---|
| WSI Classification | CAMELYON17 | 36 | May 4, 2026 |
|---|
| Multi-modal Toxicity Attack | RTP (test) | 36 | May 4, 2026 |
|---|
| Instruction Following | Alpaca SFT Small Prompts | 36 | May 4, 2026 |
|---|
| Creative Writing | Alpaca SFT Short Stories | 36 | May 4, 2026 |
|---|
| Relighting | Sunset Environment | 36 | May 1, 2026 |
|---|