Browse › Natural Language Processing › Question Answering › MedQA

Question Answering archive 2025-07-28

MedQA Benchmark (Question Answering)

27 rows 22 with code listed 1 metric Dataset page

Syntology Since the archive (Syntology): 3 placed; 17 newer papers judged to report on this board so far.

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

Direction inferred from the metric name, not from the archive: Accuracy (higher is better). Points are placed at the row's paper date, not an evaluation date; 27 of 27 rows carry one.

The chart needs JavaScript; the table below carries every value.

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 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 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 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 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 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 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 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
14 LLAMA-2 (70B) 59.2 ✓ Paper Code 2023 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
15 VOD (BioLinkBERT) 55.0 – Paper Code 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 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 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 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 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
21 BioLinkBERT (base) 40.0 – Paper Code 2022 official: harvested, nothing ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified report
22 GrapeQA: PEGA 39.51 – Paper – 2023 no code linked report
23 BioBERT (large) 36.7 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified report
24 BioBERT (base) 34.1 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 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 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
27 OPT (few-shot, k=5) 22.8 – Paper Code 2022 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 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 ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not 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. Rows whose paper has a sample that ran: 13 (13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument). Papers: 8 with a sample that ran: 8 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 13 rows with a graph line, 12 have an archive-official repository: on 9 a sample from it ran (9 with a run with no instrument failure), on 0 the samples that ran came from community repositories only, and on 2 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 94 samples: 58 ran (of which 0 constructed an object rather than computing a result; 53 with no instrument failure: 2 honoured, 0 violated, 51 with no contract checked; 5 where Syntology's instrument failed) · 36 unverified. Separately, 4 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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive: results placed by Syntology Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 22 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,588 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 17 proposed a result; of those 17, 10 gave no cell that passed the extractor's own checks, 4 were rejected by the independent check, 0 await a verdict and 3 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

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 archive rows above. Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.

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)”Caption: “Table 2 : Accuracy (%) comparison of DoG and DoG-E with different baselines on…” 3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified 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”Caption: “Table 1 : Accuracy (%) comparison of different repair methods. Δ denotes…” 2 harvested: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG arXiv:2603.03292 MA-RAG -ext 77.1 6 Feb 2026 Table 1, row “MA-RAG -ext”Caption: “Table 1: Main results (Accuracy %) on seven medical benchmarks. The […]…” 7 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified report

Syntology 3 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; under "Where in the paper" is the start of the table's caption as the paper prints it (ranking words shown as […]; a caption carrying TeX this page does not render, or quoting a percentage figure, is left to the hover and says so), and hovering there gives the caption start and each value's column header. Not part of the archive and not in the chart above. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
HijackKV: New Threat in Position-Independent KV Cache Reuse arXiv:2607.19957 22 Jul 2026 19 harvested: 9 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified refused by rules: the value is not on the scale of the leaderboard column's archive values; the quoted value appears more than once in the row
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain... arXiv:2607.17266 19 Jul 2026 3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified placed
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection arXiv:2605.28631 27 May 2026 repository linked, no samples harvested refused by a rule: one configuration gave two values for one column
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based... arXiv:2605.23414 22 May 2026 2 harvested: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified placed
COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion arXiv:2605.15016 14 May 2026 repository linked, no samples harvested rejected by the independent check
Green Shielding: A User-Centric Approach Towards Trustworthy AI arXiv:2604.24700 27 Apr 2026 7 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified refused by a rule: the model pointed at a header row
Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice... arXiv:2604.23801 26 Apr 2026 repository linked, no samples harvested refused by a rule: the value is not on the scale of the leaderboard column's archive values
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models arXiv:2604.01622 2 Apr 2026 5 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified rejected by the independent check
Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation arXiv:2604.00536 1 Apr 2026 16 harvested: 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified rejected by the independent check
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms arXiv:2604.00012 10 Mar 2026 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the model pointed at a header row
ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory arXiv:2603.26182 27 Mar 2026 4 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified refused by a rule: the value is not on the scale of the leaderboard column's archive values
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement arXiv:2603.22352 22 Mar 2026 19 harvested: 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified refused by a rule: the row is an ablation variant, not the method itself
GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning arXiv:2603.10243 10 Mar 2026 10 harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified refused by a rule: one configuration gave two values for one column
AutoAdapt: An Automated Domain Adaptation Framework for LLMs arXiv:2603.08181 9 Mar 2026 repository linked, no samples harvested refused by a rule: the model pointed at a header row
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG arXiv:2603.03292 6 Feb 2026 7 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified placed
S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs arXiv:2602.01982 2 Feb 2026 repository linked, no samples harvested refused by a rule: one configuration gave two values for one column
MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA arXiv:2602.00981 1 Feb 2026 6 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified rejected by the independent check

Syntology 17 newer papers judged to report on this board: the papers counted above as having proposed a result (3 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 10 counted above as giving no cell that passed the extractor's own checks are the 10 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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