Browse › Natural Language Processing › Question Answering › MedQA
MedQA Benchmark (Question Answering)
Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.
The archive carries no text for this table; the description above is the archive's text for the task Question Answering. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Accuracy (higher is better). Points are placed at the row's paper date; 27 of 27 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | |||||
|---|---|---|---|---|---|---|---|---|
| 1 | Med-Gemini | 91.1 | ✓ | Paper | – | 2024 | no code linked | report |
| 2 | GPT-4 | 90.2 | ✓ | Paper | Code | 2023 | 9 of 10 ran · 1 unverified | report |
| 3 | Med-PaLM 2 | 85.4 | – | Paper | Code | 2023 | linked, not harvested | report |
| 4 | Med-PaLM 2 (CoT + SC) | 83.7 | – | Paper | Code | 2023 | linked, not harvested | report |
| 5 | Med-PaLM 2 (5-shot) | 79.7 | – | Paper | Code | 2023 | linked, not harvested | report |
| 6 | MedMobile (3.8B) | 75.7 | ✓ | Paper | Code | 2024 | linked, not harvested | report |
| 7 | Meerkat-7B | 74.3 | ✓ | Paper | – | 2024 | no code linked | report |
| 8 | Meerkat-7B (Single) | 70.6 | ✓ | Paper | – | 2024 | no code linked | report |
| 9 | Meditron-70B (CoT + SC) | 70.2 | – | Paper | Code | 2023 | 9 of 14 ran · 5 unverified | report |
| 10 | Flan-PaLM (540 B) | 67.6 | – | Paper | Code | 2022 | linked, not harvested | report |
| 11 | LLAMA-2 (70B SC CoT) | 61.5 | ✓ | Paper | Code | 2023 | 9 of 14 ran · 5 unverified | report |
| 12 | Shakti-LLM (2.5B) | 60.3 | – | Paper | – | 2024 | no code linked | report |
| 13 | Codex 5-shot CoT | 60.2 | – | Paper | Code | 2022 | 10 of 10 ran · 0 unverified | report |
| 14 | LLAMA-2 (70B) | 59.2 | ✓ | Paper | Code | 2023 | 9 of 14 ran · 5 unverified | report |
| 15 | VOD (BioLinkBERT) | 55.0 | – | Paper | Code | 2022 | 1 of 1 ran · 0 unverified | report |
| 16 | BioMedGPT-10B | 50.4 | – | Paper | Code | 2023 | linked, not harvested | report |
| 17 | PubMedGPT (2.7 B) | 50.3 | – | Paper | Code | 2022 | linked, not harvested | report |
| 18 | DRAGON + BioLinkBERT | 47.5 | – | Paper | Code | 2022 | 3 of 18 ran · 15 unverified | report |
| 19 | BioLinkBERT (340 M) | 45.1 | – | Paper | Code | 2022 | linked, not harvested | report |
| 20 | GAL 120B (zero-shot) | 44.4 | – | Paper | Code | 2022 | 2 of 2 ran · 0 unverified | report |
| 21 | BioLinkBERT (base) | 40.0 | – | Paper | Code | 2022 | 3 of 14 ran · 11 unverified | report |
| 22 | GrapeQA: PEGA | 39.51 | – | Paper | – | 2023 | no code linked | report |
| 23 | BioBERT (large) | 36.7 | – | Paper | Code | 2019 | 13 of 25 ran · 12 unverified | report |
| 24 | BioBERT (base) | 34.1 | – | Paper | Code | 2019 | 13 of 25 ran · 12 unverified | report |
| 25 | GPT-Neo (2.7 B) | 33.3 | – | Paper | Code | 2022 | linked, not harvested | report |
| 26 | BLOOM (few-shot, k=5) | 23.3 | – | Paper | Code | 2022 | 2 of 2 ran · 0 unverified | report |
| 27 | OPT (few-shot, k=5) | 22.8 | – | Paper | Code | 2022 | 2 of 2 ran · 0 unverified | report |
All 27 rows shown. 27 link to a paper page on this site; 7 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 13 rows have a graph line, from 8 distinct papers; 13 rows (8 papers) have at least one sample that ran. Counting each paper once: Syntology ran 50 of 94 samples; 44 unverified. Separately, 1 of those 94 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-25. Per-sample status is on the paper page.
Since the archive: results placed by Syntology Syntology
Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the rows above. Measured before publishing: the extractor was run on 883 held-out archive papers and processed 881 of them (the other 2 failed with an error before producing any output and are not part of this measurement); on those 881 papers, a blind reviewer judged 108 of 110 accepted entries correct (95% lower confidence bound 0.9361). Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.
| Paper | Method (configuration) | Accuracy | Date | Where in the paper | Code Syntology | Report |
|---|---|---|---|---|---|---|
| Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on... arXiv:2607.17266 | DoG (Ours) · GPT | 81.5 | 19 Jul 2026 | Table 2, row “DoG (Ours)” | 3 of 3 ran | report |
| When Planning Fails Despite Correct Execution: On Epistemic Calibration for... arXiv:2605.23414 | EPC-AW | 74.11 | 22 May 2026 | Table 1, row “EPC-AW” | 2 of 2 ran | report |
Syntology 2 entries, one per paper, newest first by month (the arXiv date, else the month in the arXiv id), then by arXiv id. Each value is the cell text as the paper prints it; hover "Where in the paper" for the table's caption and each value's column header. Not part of the archive and not in the chart above. Drawn from 6,885 of 9,623 newer papers checked so far.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections