Codesota · Models · OLMo-2-7B-1124 (olmOCR-peS2o)5 results · 5 benchmarks
Model card
OLMo-2-7B-1124 (olmOCR-peS2o).
unknown
§ 02 · Benchmarks
Every benchmark OLMo-2-7B-1124 (olmOCR-peS2o) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Natural Questions | Natural Language Processing · Question Answering | accuracy | 29.1% | #3 | — | source ↗ |
| 02 | DROP | Natural Language Processing · Question Answering | f1 | 43.7% | #5 | — | source ↗ |
| 03 | WinoGrande | Reasoning · Commonsense Reasoning | accuracy | 58.0% | #13 | — | source ↗ |
| 04 | HellaSwag | Reasoning · Commonsense Reasoning | accuracy | 62.6% | #17 | — | source ↗ |
| 05 | MMLU | Reasoning · Commonsense Reasoning | accuracy | 61.1% | #59 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where OLMo-2-7B-1124 (olmOCR-peS2o) actually performs.
§ 04 · Papers
1 paper with results for OLMo-2-7B-1124 (olmOCR-peS2o).
- 2025-02-25· 5 results
olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
5
results
0 of 5 rows marked verified.