RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 3 Flash

6 benchmarks · 6 observations · 6 sources · released 2025-12-17

Scores at a glance

6 benchmarks · large dot: Gemini 3 Flash; small dots: closest models where reported

OmniDocBench ↗92.62 points
78.4496.91

Gemini 3 Flash · OmniDocBench · Overall parsing score · end-to-end evaluation ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

51.7 percentile-point gap

4 of 5 shared benchmark comparisons

59.2 percentile-point gap

3 of 5 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning — published result table ↗

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh et al. · 2026

    All 13 authors

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh, Oertell, Owen, Portes, Jacob, Havens, Sam, Elsen, Erich, Bendersky, Michael, Zaharia, Matei, Chen, Xing

  2. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  3. AI benchmarks & capabilities ↗

    Epoch AI

  4. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  5. SWE Atlas - Refactoring — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  6. OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations — published result table ↗

    Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin et al. · 2024

    All 20 authors

    Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, Jin Shi, Fan Wu, Pei Chu, Minghao Liu, Zhenxiang Li, Chao Xu, Bo Zhang, Botian Shi, Zhongying Tu, Conghui He

Names used in source tables

Gemini 3 Flash · Gemini 3 Flash (Mini-SWE-Agent) · Gemini-3-Flash (Mini-SWE-Agent)