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 |
|---|---|---|---|---|---|
| Multimodal Perception | MME | 42 | Jun 24, 2026 | ||
| Uncertainty Estimation | emrQA | 42 | May 8, 2026 | ||
| Uncertainty Estimation | NewsQA | 42 | May 8, 2026 | ||
| Question Answering | MMLU Pro.Med. | 42 | May 8, 2026 | ||
| Generation correctness prediction | TruthfulQA (test) | 42 | May 7, 2026 | ||
| Generation correctness prediction | TriviaQA (test) |
| 42 |
| May 7, 2026 |
| Generation correctness prediction | SciQ (test) | 42 | May 7, 2026 |
|---|
| Generation correctness prediction | SciQ | 42 | May 7, 2026 |
|---|
| Light Field Super-Resolution | STFgantry | 42 | Jul 2, 2026 |
|---|
| Light Field Super-Resolution | INRIA | 42 | Jul 2, 2026 |
|---|
| Light Field Super-Resolution | HCI old | 42 | Jul 2, 2026 |
|---|
| Light Field Super-Resolution | HCI new | 42 | Jul 2, 2026 |
|---|
| Light Field Super-Resolution | EPFL | 42 | Jul 2, 2026 |
|---|
| Safety Evaluation | AdvBench Safety Evaluation | 42 | May 7, 2026 |
|---|
| Safety Evaluation | CategoricalHarmfulQA Alpaca fine-tuning (test) | 42 | May 7, 2026 |
|---|
| Jailbreak Attack | AdvBench | 42 | May 7, 2026 |
|---|
| Jailbreak Attack | AdvBench gray-box setting | 42 | May 7, 2026 |
|---|
| Summarization | XSum | 42 | May 26, 2026 |
|---|
| Video Temporal Grounding | Charades-STA | 42 | Jul 8, 2026 |
|---|
| Programming | LiveCodeBench V3 V4 (test) | 42 | May 6, 2026 |
|---|
| Mathematical Reasoning | AIME 2025-2026 (test) | 42 | May 6, 2026 |
|---|
| Tool-use Factuality Evaluation | BFCL Task | 42 | May 4, 2026 |
|---|
| Tool-use Factuality Evaluation | InvivoQuery | 42 | May 4, 2026 |
|---|
| Tool-use Factuality Evaluation | Entity Task | 42 | May 4, 2026 |
|---|
| CBCT Reconstruction | AAPM Clinical Dataset 60-view | 42 | May 1, 2026 |
|---|