Evaluation

ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026)

Evidence concern: excluded from comparisons

Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4

Published inference benchmark; transcribed, not reproduced.

Evaluation results

1 evaluation · 12 results. Different protocols are not a single leaderboard.

Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) · Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)

Sorted by Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 1024 tokens) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 1024 tokens)	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 2048 tokens)	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 256 tokens)	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 4096 tokens)	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 512 tokens)	Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 8192 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 1024 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 2048 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 256 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 4096 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 512 tokens)	Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 8192 tokens)
ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)Evaluation	212	203	224	186	218	154	673	332	2721	161	1356	67

All 12 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	673 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 1024 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 1024, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	212 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 1024 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 1024, column 'tokens/s'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	332 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 2048 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 2048, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	203 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 2048 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 2048, column 'tokens/s'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	2720 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 256 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 256, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	224 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 256 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 256, column 'tokens/s'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	161 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 4096 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 4096, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	186 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 4096 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 4096, column 'tokens/s'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	1360 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 512 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 512, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	218 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 512 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 512, column 'tokens/s'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	67 Maximum batch size (Encoder forward pass on one A100 80 GB; sequence length 8192 tokens) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 8192, column 'bs'
Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)	Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2) Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)	154 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 8192 tokens) sample-per-second · higher Uncertainty: Not reported by the source: Mean of 10 timing runs; spread not printed Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Appendix B Table 2 and Figure 1 (axis 'Inference speed (tokens/s)') give throughput in tokens/s, but the printed values are inconsistent with the printed batch sizes: ModernGENA base (FA2 + autocast bf16) at L = 256 prints 552.44 tokens/s with a batch of 3,631 sequences (929,536 tokens), about 28 minutes per batch, and ModernGENA base without FA2 at L = 8192 prints 71.15 tokens/s with a batch of 92 (753,664 tokens), about 2.9 hours per batch, against a stated pretraining throughput of 1.33M tokens/s on eight A100 GPUs (Section 3.2.4). The unit or scale of the throughput column is unclear. Batch sizes share the table. Values are recorded as printed.Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9); Figure 1 (page 4); Section 3.2.4 Methods, coverage and source ModernGENA large (FA2 + autocast bf16) (377M) inference throughput on one A100 (Aspidova et al. 2026) model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Aggregation: Not reported Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'ModernGENA large (FA2 + autocast bf16) (377M)', sequence length L = 8192, column 'tokens/s'

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-23-5347695500ed · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2)

Configuration: ModernGENA large (FA2 + autocast bf16) on one A100 80 GB (Aspidova et al. 2026)
Protocol: DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2)
Dataset: Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)

origin: Author-reported evaluation
configuration: Primary source as retrieved 2026-10-11
protocol id: model-execution-20261011-protocol-aspidova2026-a100-inference-throughput
dataset version: Not reported
split: Fixed-length inputs, L = 256 to 8192 tokens
population: Fixed-length token sequences
inputs: Token sequences
adaptation: None (pretrained encoder, forward pass only)
metric implementation: Maximum batch size by exponential growth and binary search; mean of 10 timing runs
aggregation: Mean of 10 timing runs per model and length
budget: One NVIDIA A100 80 GB GPU

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: Fixed-length inputs, L = 256 to 8192 tokens
Adaptation: None (pretrained encoder, forward pass only)
Scoring implementation: Maximum batch size by exponential growth and binary search; mean of 10 timing runs

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

18 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance
Comparison: adaptation None (pretrained encoder, forward pass only) Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: aggregation Mean of 10 timing runs per model and length Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: budget One NVIDIA A100 80 GB GPU Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: dataset version Not reported Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	missing or unspecified No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: inputs Token sequences Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: metric implementation Maximum batch size by exponential growth and binary search; mean of 10 timing runs Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.metric_implementation` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: population Fixed-length token sequences Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.population` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: protocol id model-execution-20261011-protocol-aspidova2026-a100-inference-throughput Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.protocol_id` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Comparison: split Fixed-length inputs, L = 256 to 8192 tokens Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.comparison.split` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact
Origin author_reported Context-only references	Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Original source ↗ Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)' Version: bioRxiv preprint version 1, posted 2026-04-23 Retrieved: 2026-10-11T21:39:38Z	not individually reviewed No individual claim review recorded author reported Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.origin` Source artifact SHA-256: `238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa` Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Original source · bioRxiv preprint version 1, posted 2026-04-23

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: model-execution-20261011-eval-aspidova2026-moderngena-large-fa2-bf16

areas: dna-genomes
contexts: research
origin: author_reported
protocol: model-execution-20261011-protocol-aspidova2026-a100-inference-throughput
version: Primary source as retrieved 2026-10-11
comparison: protocol id: model-execution-20261011-protocol-aspidova2026-a100-inference-throughput; dataset version: Not reported; split: Fixed-length inputs, L = 256 to 8192 tokens; population: Fixed-length token sequences; inputs: Token sequences; adaptation: None (pretrained encoder, forward pass only); metric implementation: Maximum batch size by exponential growth and binary search; mean of 10 timing runs; aggregation: Mean of 10 timing runs per model and length; budget: One NVIDIA A100 80 GB GPU
source locator: Appendix B Table 2 row 'ModernGENA large (FA2 + autocast bf16) (377M)'
missing metadata: comparison.dataset version: reason: unreported

Related records

Suggest a correction