Browse › Methodology › Multi-task Language Understanding › MGSM

Multi-task Language Understanding archive 2025-07-28

MGSM Benchmark (Multi-task Language Understanding)

12 rows 11 with code listed 1 metric Dataset page

Syntology Since the archive (Syntology): none placed; 7 newer papers judged to report on this board so far.

The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. https://arxiv.org/pdf/2009.03300.pdf

The archive carries no text for this table; the description above is the archive's text for the task Multi-task Language Understanding. archive 2025-07-28

Over time archive 2025-07-28

Not inferred: Average (%). Points are placed at the row's paper date, not an evaluation date; 12 of 12 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 PaLM 2 (few-shot, k=8, SC) 87.0 – Paper Code 2023 linked, not harvested report
2 PaLM 2 (8-shot, CoT) 72.2 – Paper Code 2023 linked, not harvested report
3 Flan-PaLM 540B (8-shot, fine-tuned, CoT + SC) 72.0 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
4 Flan-U-PaLM 540B (CoT) 60.4 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
5 Flan-PaLM 540B (8-shot, fine-tuned, CoT) 57.0 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
6 PaLM 540B 55.0 – Paper Code 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified report
7 U-PaLM 540B (CoT) 49.9 – Paper – 2022 no code linked report
8 text-davinci-003 36 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
9 code-davinci-002 35 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
10 text-davinci-002 23.7 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
11 Flan-PaLM 540B (8-shot, fine-tuned) 21.2 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report
12 GPT-3 Davinci 175B 5.7 – Paper Code 2022 8 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; 7 where Syntology's instrument failed) · 9 unverified report

All 12 rows shown. 12 link to a paper page on this site; 0 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). 9 rows have a graph line, from 2 distinct papers. Rows whose paper has a sample that ran: 9 (9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument). Papers: 2 with a sample that ran: 2 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 9 rows with a graph line, 0 have an archive-official repository: on 0 a sample from it ran (0 with a run with no instrument failure), on 0 the samples that ran came from community repositories only, and on 0 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 54 samples: 40 ran (of which 17 constructed an object rather than computing a result; 25 with no instrument failure: 2 honoured, 1 violated, 22 with no contract checked; 15 where Syntology's instrument failed) · 14 unverified. Separately, 2 of those 54 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 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), 10 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 1,592 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 7 proposed a result; of those 7, 6 gave no cell that passed the extractor's own checks, 1 was rejected by the independent check, 0 await a verdict and 0 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.

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
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored... arXiv:2606.25821 24 Jun 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 table's column header does not name the leaderboard's metric
GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs arXiv:2604.23626 26 Apr 2026 16 harvested: 11 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified rejected by the independent check
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model... arXiv:2604.12374 14 Apr 2026 24 harvested: 20 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons arXiv:2602.01283 1 Feb 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning arXiv:2601.17671 25 Jan 2026 6 harvested: 3 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; 2 where Syntology's instrument failed) · 3 unverified refused by a rule: the row is an ablation variant, not the method itself
Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert... arXiv:2601.14050 20 Jan 2026 repository linked, no samples harvested refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
mR3: Multilingual Rubric-Agnostic Reward Reasoning Models arXiv:2510.01146 1 Oct 2025 1 harvested: 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 refused by a rule: the number the model quoted is not the number printed in the cell it pointed at

Syntology 7 newer papers judged to report on this board: the papers counted above as having proposed a result (0 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 6 counted above as giving no cell that passed the extractor's own checks are the 6 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