RLTasksby ulam.ai
Models / Reported model

Reported model / MODEL EVIDENCE

Mantis-Idefics2

2 benchmarks · 2 observations · 2 sources

Scores at a glance

2 benchmarks · large dot: Mantis-Idefics2; small dots: closest models where reported

PhysBench ↗37.39%
31.6851.94

Mantis-Idefics2 · PhysBench · Overall accuracy · physical-world question answering ↗

Closest models by score

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

There are not enough shared scored settings to identify close comparisons reliably.

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. LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding — published result table ↗

    Haoning Wu, Dongxu Li, Bei Chen, Junnan Li · 2024

  2. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding — published result table ↗

    Chow, Wei, Mao, Jiageng, Li, Boyi, Seita, Daniel, Guizilini, Vitor, Wang, Yue · 2025

Names used in source tables

Mantis-Idefics2