Contested result

ESM-1v and ESM-2: ProteinGym AMFR assay-level Spearman comparison reverses the order

Medium severity
Not yet reviewed
Ordering reversal
Same task, different protocols

ProteinGym AMFR assay-level Spearman comparison ranks ESM-2 above ESM-1v in 15 of 17 comparisons; other studies rank ESM-1v above ESM-2 in 10 of 11.

An automatic lead, not a finding of error. The results below are shown as published, everywhere on the site, until a reviewer decides otherwise.

Which studies agree

2 papers rank ESM-1v above ESM-2 in 10 of their 12 comparisons and ESM-2 higher in 1; 1 is a tie. ProteinGym AMFR assay-level Spearman… ranks ESM-2 above ESM-1v in 15 of its 19 comparisons and ESM-1v higher in 2; 2 are ties.

Rank ESM-1v higher (2): Livesey and Marsh 2025, ProteinGym
Rank ESM-2 higher (1): ProteinGym AMFR assay-level Spearman… (disagrees)
Mixed (0): none

Each paper sits where at least two thirds of its comparisons point; Mixed means neither model reaches two thirds. The larger, outlined dot is the paper that disagrees.

ESM-1v higherTieESM-2 higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.

Papers compared (3)
Paper	Role	Ranks ESM-1v higher	Ranks ESM-2 higher	Ties
ProteinGym AMFR assay-level Spearman comparison and 4 more records · Repository	Disagrees	2	15	2
Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML) and 1 more record · DOI	Agrees	7	0	0
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Source	Agrees	3	1	1

Comparisons in ProteinGym AMFR assay-level Spearman… (19)

Protocol	Dataset	Metric	ESM-1v	ESM-2	Higher
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman), unitless	0.42	0.425	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman), unitless	0.32	0.337	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman), unitless	0.429	0.415	ESM-1v
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman), unitless	0.495	0.513	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Human proteins: mean over proteins of assay-level Spearman), unitless	0.458	0.457	Tie
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman), unitless	0.316	0.341	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman), unitless	0.409	0.423	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Organismal fitness assays: mean over proteins of assay-level Spearman), unitless	0.386	0.387	Tie
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman), unitless	0.464	0.486	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman), unitless	0.413	0.458	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman), unitless	0.477	0.523	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman), unitless	0.294	0.333	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)), unitless	0.407	0.414	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman), unitless	0.403	0.422	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman), unitless	0.215	0.248	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman), unitless	0.177	0.219	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman), unitless	0.153	0.173	ESM-2
ProteinGym v1.3 zero-shot DMS substitutions	ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman), unitless	0.218	0.234	ESM-2
ProteinGym AMFR official zero-shot Spearman snapshot	ProteinGym AMFR 4G3O official snapshot cohort	Spearman, unitless	0.423	0.321	ESM-1v

Comparisons in Livesey and Marsh 2025 (7)

Protocol	Dataset	Metric	ESM-1v	ESM-2	Higher
Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense	Livesey and Marsh 2025 clinical set: ClinVar pathogenic versus gnomAD v4.1 missense (819 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, per-protein AUROC on shared variants, ClinVar P/LP versus gnomAD v4.1 missense, proteins with at least 10 of each), percent	61.4	51.4	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, 36 human DMS sets), percent	81.5	72.2	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against the five top-ranked VEPs (column top_5_winrate; the five are not listed in the table), \|Spearman\| with DMS on shared variants, 36 human DMS sets), percent	28.1	27.8	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, direct assays only	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, direct DMS assays only), percent	78.4	74.2	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, indirect assays only	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, indirect DMS assays only), percent	83.6	70.8	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions only	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, SNV-accessible substitutions only), percent	81.5	70.5	ESM-1v
Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions with gaps filled	Livesey and Marsh 2025 human DMS benchmark set (36 proteins)	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score), percent	81.8	71.1	ESM-1v

Comparisons in ProteinGym (5)

Protocol	Dataset	Metric	ESM-1v	ESM-2	Higher
ProteinGym ZS-SUB-AUC: Zero-shot substitutions, AUC	ProteinGym substitution DMS assays (ProteinGym split)	AUROC, unitless	0.723	0.72	Tie
ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC	ProteinGym substitution DMS assays (ProteinGym split)	MCC, unitless	0.32	0.314	ESM-1v
ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10%	ProteinGym substitution DMS assays (ProteinGym split)	NDCG at 10%, unitless	0.749	0.759	ESM-2
ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall	ProteinGym substitution DMS assays (ProteinGym split)	Top 10% recall, fraction	0.211	0.208	ESM-1v
ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman	ProteinGym substitution DMS assays (ProteinGym split)	Spearman, unitless	0.407	0.401	ESM-1v

What disagrees

Other studies: rank ESM-1v above ESM-2 in 10 of 11 comparisons
This study: ranks ESM-2 above ESM-1v in 15 of 17 comparisons

Compared: ESM-1v, ESM-2
Study that disagrees: ProteinGym AMFR assay-level Spearman comparison, ProteinGym clinical supervised substitutions AUC summary at commit 144fe22, ProteinGym clinical zero-shot indels AUC summary at commit 144fe22, ProteinGym clinical zero-shot substitutions AUC summary at commit 144fe22, ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22
Other studies: ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design, Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML), Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8)
Rule: Ordering reversal; same task, different protocols
Model identity: Matched across studies partly through links not yet reviewed

The compared numbers

Each value links to its result record and source. Compare values within one protocol; the rule compares rankings, not raw values across protocols.

In the study that disagrees (35)
Study	Tool	Protocol or benchmark	Metric	Value
ProteinGym AMFR assay-level Spearman comparison; Protocol metadata evidence: proteingym-reference_files-DMS_substitutions.csv	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym AMFR official zero-shot Spearman snapshot	Spearman	0.423
ProteinGym AMFR assay-level Spearman comparison; Protocol metadata evidence: proteingym-reference_files-DMS_substitutions.csv	ESM2 (150M) [ProteinGym 144fe22b snapshot]	ProteinGym AMFR official zero-shot Spearman snapshot	Spearman	0.321
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays))	0.407
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman)	0.403
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.215
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.153
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.218
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman)	0.42
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman)	0.32
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman)	0.429
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman)	0.477
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman)	0.495
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman)	0.316
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman)	0.409
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman)	0.464
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman)	0.413
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (ensemble) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman)	0.294
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM-1v (single) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.177
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (15B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.219
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (15B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.173
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (15B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.234
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (15B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman)	0.341
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (15B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman)	0.333
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (3B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman)	0.423
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (3B) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman)	0.458
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays))	0.414
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman)	0.422
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman)	0.248
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman)	0.425
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman)	0.337
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman)	0.415
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman)	0.523
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman)	0.513
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman)	0.486
ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22; Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py	ESM2 (650M) [ProteinGym 144fe22b snapshot]	ProteinGym v1.3 zero-shot DMS substitutions	Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman)	0.458

In the other studies (22)
Study	Tool	Protocol or benchmark	Metric	Value
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-1v (ensemble)	ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC	MCC	0.32
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-1v (ensemble)	ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10%	NDCG at 10%	0.749
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-1v (ensemble)	ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall	Top 10% recall	0.211
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-1v (ensemble)	ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman	Spearman	0.407
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-2 (15B)	ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC	MCC	0.314
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-2 (15B)	ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10%	NDCG at 10%	0.759
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-2 (15B)	ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall	Top 10% recall	0.208
ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design	ESM-2 (15B)	ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman	Spearman	0.401
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense	Pairwise win rate (average pairwise win rate against all other VEPs, per-protein AUROC on shared variants, ClinVar P/LP versus gnomAD v4.1 missense, proteins with at least 10 of each)	61.4
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 clinical benchmark: pairwise AUROC win rate, ClinVar pathogenic versus gnomAD missense	Pairwise win rate (average pairwise win rate against all other VEPs, per-protein AUROC on shared variants, ClinVar P/LP versus gnomAD v4.1 missense, proteins with at least 10 of each)	51.4
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, 36 human DMS sets)	81.5
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Pairwise win rate (average pairwise win rate against the five top-ranked VEPs (column top_5_winrate; the five are not listed in the table), \|Spearman\| with DMS on shared variants, 36 human DMS sets)	28.1
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, 36 human DMS sets)	72.2
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, all 36 DMS sets	Pairwise win rate (average pairwise win rate against the five top-ranked VEPs (column top_5_winrate; the five are not listed in the table), \|Spearman\| with DMS on shared variants, 36 human DMS sets)	27.8
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, direct assays only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, direct DMS assays only)	78.4
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, direct assays only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, direct DMS assays only)	74.2
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, indirect assays only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, indirect DMS assays only)	83.6
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, indirect assays only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, indirect DMS assays only)	70.8
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, SNV-accessible substitutions only)	81.5
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions only	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS on shared variants, SNV-accessible substitutions only)	70.5
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM-1v (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions with gaps filled	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score)	81.8
Livesey and Marsh 2025, Supplementary Material 2 (Tables S1-S8); Livesey and Marsh 2025, Genome Biology 26:104 (Europe PMC full text XML)	ESM2 (Livesey and Marsh 2025)	Livesey and Marsh 2025 DMS benchmark: pairwise \|Spearman\| win rate, SNV-accessible substitutions with gaps filled	Pairwise win rate (average pairwise win rate against all other VEPs, \|Spearman\| with DMS, SNV-accessible substitutions, missing predictions filled with the VEP's most benign score)	71.1

Follow-up

Current state: Not yet reviewed.

No one has reviewed this finding yet.

How to help resolve this

If you know why these studies disagree, for example a different population, metric or preprocessing step, or you have a corrected value, tell us through the contribution form. A reviewer checks every submission against its source before anything changes, and the step is added to the follow-up above.

Finding discrepancy-6e0a1543c1c68a64 · All contested results · How findings are made and followed up