Pith. sign in

REVIEW 5 cited by

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2508.17472 v1 pith:QVKL673M submitted 2025-08-24 cs.CV

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

classification cs.CV
keywords benchmarkgenerationimagemodelsproposereasoningt2i-reasonbenchtext-to-image
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose T2I-ReasonBench, a benchmark evaluating reasoning capabilities of text-to-image (T2I) models. It consists of four dimensions: Idiom Interpretation, Textual Image Design, Entity-Reasoning and Scientific-Reasoning. We propose a two-stage evaluation protocol to assess the reasoning accuracy and image quality. We benchmark various T2I generation models, and provide comprehensive analysis on their performances.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Do Image Editing Models Understand Lighting?

    cs.CV 2026-06 unverdicted novelty 7.0

    New 3DLP benchmark with real-world 1K HDR pairs shows state-of-the-art image editing models vary in physical lighting consistency, with best models close to reality but error-prone in low-light regions.

  2. More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage

    cs.CL 2026-04 unverdicted novelty 7.0

    Vision-language models exhibit literal superiority bias on noun compounds, with photorealistic visuals linked to poorer idiomatic grounding via new DIVA benchmark and Δ metric.

  3. SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces SciIR-82k dataset and SciIR-Bench for scientific image reasoning generation organized by Peirce's semiotic triad, with fine-tuning raising model score from 35% to 43%.

  4. Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces FEPBench benchmark to evaluate T2I models on instruction faithfulness, reasoning enrichment, and semantic precision for natural-science illustrations using atom set annotations.

  5. Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation

    cs.CV 2026-05 unverdicted novelty 6.0

    Qwen-Image-Bench introduces a hierarchical creator-centric benchmark with 1000 prompts, 23 sub-capabilities, and a Q-Judger model that scores images on 56 verifiable facets to distinguish T2I models on fidelity and cr...