Paper Citation Record · LEDGER

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

As of 20 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 28 inbound Pith citation observations for arXiv:2502.09696.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.09696 v3

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T20:55:05.990141Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 28 of 28 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:12:18.449858Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T08:49:41.640745Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy4
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 98444cc0-8a68-4581-9a43-5f5448bd715e · outbound

This paper cites Pixtral 12B.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Pixtral 12B

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.814584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d1fe0e-2467-4eee-b831-d50c64ba0559 · outbound

This paper cites Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.825741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1536fbc9-d5a1-4d3d-bd9a-969cd4e1f9d7 · outbound

This paper cites GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.830828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a508fc-13af-4426-b05b-96e52b647042 · outbound

This paper cites On the Measure of Intelligence.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models On the Measure of Intelligence

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.836265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f40461b-8772-4bd8-bff0-5f1e3331a42c · outbound

This paper cites ARC Prize 2024: Technical Report.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models ARC Prize 2024: Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.841893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 767a398d-e1af-4f8b-a53c-584161bc72c7 · outbound

This paper cites NVLM: Open Frontier-Class Multimodal LLMs.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models NVLM: Open Frontier-Class Multimodal LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.847019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99fdb64f-d6ee-4be9-a54d-e96b954eae30 · outbound

This paper cites The Llama 3 Herd of Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.852088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ae0c76-dba4-46b9-8e4a-787f01ddfc51 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Measuring Massive Multitask Language Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.857068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ae7121-fab0-4754-8a54-8f688185c808 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.871183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98842e2d-20fb-41ae-86cc-e0076730f568 · outbound

This paper cites A Survey on Benchmarks of Multimodal Large Language Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models A Survey on Benchmarks of Multimodal Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.875661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2700c133-03ac-4b66-9c79-01c30d5e6daf · outbound

This paper cites Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.885072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d61ac6b-2eba-4b79-ac24-e0bce58fc303 · outbound

This paper cites LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.890289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62238fca-fcb3-4dbc-b782-a8949f7f8a78 · outbound

This paper cites Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.895061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f7a737-f74a-40f8-9644-b349ecab8e7f · outbound

This paper cites Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.905698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9210a240-a627-4828-81f3-7bdd2adda71f · outbound

This paper cites Humanity's Last Exam.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Humanity's Last Exam

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.910610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d65d81-e54e-430e-9d2d-426f45546a9b · outbound

This paper cites Does Spatial Cognition Emerge in Frontier Models?.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Does Spatial Cognition Emerge in Frontier Models?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.915677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 101bd3a9-40fa-4a20-b044-78c85ba72525 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.920807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e3135e-90b7-4461-ad0c-40efa29d97a5 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.926142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72595cfc-cc34-4337-9f94-be24665ba15d · outbound

This paper cites Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.932609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8f6fce-5fe8-4b96-b52e-dc6f83720153 · outbound

This paper cites GRAB: A Challeng- ing GRaph Analysis Benchmark for Large Multimodal Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models GRAB: A Challeng- ing GRaph Analysis Benchmark for Large Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.938073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516db7e5-ea15-4bea-b862-da5dfe2b613d · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.942731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0effa166-3eca-4f2c-b395-f6d51264615f · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.948087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e23e631-42cf-44a5-9e20-f6532ec450be · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Gemini: A Family of Highly Capable Multimodal Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.953189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b145c7-c349-4126-9bcd-10a7ae592afe · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.958169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b19d9eb-6c8a-4aa5-88c9-bd1656193ae2 · outbound

This paper cites TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.971251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d9b4615-be23-4171-8b8a-227386e1cbac · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.975587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4757463-6499-4e27-a1ea-883ca2a50071 · outbound

This paper cites A Benchmark for Compositional Visual Reasoning.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models A Benchmark for Compositional Visual Reasoning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.979890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781a1daf-41e5-4c0d-a0d0-9b7e712c6709 · outbound

This paper cites HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.985112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27902e1d-21ee-4f6e-ab39-e9afcad13154 · outbound

This paper cites Note, o1 pro was accessed through the ChatGPT interface preventing hyperparameter configuration.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Note, o1 pro was accessed through the ChatGPT interface preventing hyperparameter configuration

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T20:55:06.672110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f9ad8685-9bee-4776-b457-bda53e46d68d · outbound

This paper cites Scaling Scaling Laws with Board Games.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Scaling Scaling Laws with Board Games

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.861532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd7ad324-428f-48a6-baaf-1f530e6f3ee4 · outbound

This paper cites LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.967050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43499bb-492b-4552-8110-d242ea5d55db · outbound

This paper cites Hello gpt-4o | openai.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Hello gpt-4o | openai

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T20:55:06.712697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b1173d92-1231-48ed-a417-87fc67c79050 · outbound

This paper cites Transformers: State-of- the-Art Natural Language Processing.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Transformers: State-of- the-Art Natural Language Processing

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T20:55:06.688633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a2877bd8-df52-4cf0-ad51-32bb199e8e0e · outbound

This paper cites ReMI: A Dataset for Reasoning with Multiple Images.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models ReMI: A Dataset for Reasoning with Multiple Images

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.866702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc69712-5543-4614-923e-709f5745dddf · outbound

This paper cites Mistral AI API (0.0.2).

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Mistral AI API (0.0.2)

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T20:55:06.732765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 344fff01-4e55-47a8-a7fc-0618645bdd97 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T20:55:05.879967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d3d2f3e0-0ea2-4655-82f3-ded6840c9ba8 · inbound

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization cites this paper.

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6328a92d-895e-4871-86f7-8f7f54284b80 · inbound

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models cites this paper.

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-16T05:12:18.449858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34766d48-582d-4b35-a054-ef7c618cf600 · inbound

SCAN: Structured Capability Assessment and Navigation for LLMs cites this paper.

SCAN: Structured Capability Assessment and Navigation for LLMs ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e3f32080-9df0-49f2-8ed2-11638ecb1d4e · inbound

Seed1.5-VL Technical Report cites this paper.

Seed1.5-VL Technical Report ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 114

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 85185ae9-fdde-4a62-abc9-5b7fa633c212 · inbound

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models cites this paper.

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 125

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:19.618321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72ce693f-81b5-4041-8af2-6027aa1b2613 · inbound

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning cites this paper.

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f374187d-769d-4084-8ca9-cceac74b5a30 · inbound

Kwai Keye-VL Technical Report cites this paper.

Kwai Keye-VL Technical Report ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T20:45:08.961173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5d77b1-ae26-4692-935b-c591748238e0 · inbound

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cites this paper.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9bc0b383-70dc-41d8-b6f7-78728df2e511 · inbound

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model cites this paper.

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T13:24:39.784349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a4d9b5-34ab-4d86-b96c-42772aa0706f · inbound

Kwai Keye-VL 1.5 Technical Report cites this paper.

Kwai Keye-VL 1.5 Technical Report ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T12:28:30.182788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2747362-ce7e-4f6a-8c54-10ba720e97b6 · inbound

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks cites this paper.

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T11:56:10.885010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6b1e8b0-932f-4649-a42a-c00b089b2f09 · inbound

Kimi K2.5: Visual Agentic Intelligence cites this paper.

Kimi K2.5: Visual Agentic Intelligence ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fbd72c36-3362-4fad-a307-7bb6779e68a9 · inbound

Seed1.8 Model Card: Towards Generalized Real-World Agency cites this paper.

Seed1.8 Model Card: Towards Generalized Real-World Agency ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7eed3b2b-8d9c-4ee8-9ac6-a42438f9b796 · inbound

Self-Distilled RLVR cites this paper.

Self-Distilled RLVR ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e2b0a151-a2cf-4c5c-9912-ebf4ada0572b · inbound

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models cites this paper.

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 88

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 550446f8-6f7c-4807-91e4-2dbc659f2889 · inbound

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models cites this paper.

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-12T22:48:45.647588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb8cab9e-44fe-49df-b047-586e83a01698 · inbound

Qwen3.5-Omni Technical Report cites this paper.

Qwen3.5-Omni Technical Report ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3d0e8800-e10b-491f-b257-ef0e97432a72 · inbound

Near-Future Policy Optimization cites this paper.

Near-Future Policy Optimization ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 59bade78-b347-4887-87ec-819ddbbc3e3d · inbound

Co-Evolving Policy Distillation cites this paper.

Co-Evolving Policy Distillation ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4bbfcb8f-eadb-4b75-a59b-a251d94b360b · inbound

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion cites this paper.

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 263ef561-e9fc-44e6-819e-76f2f5c527ef · inbound

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR cites this paper.

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 128

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 07df2b79-d2d4-4633-b939-2629537ab74e · inbound

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark cites this paper.

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 144

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a0a912cf-793d-4413-8cd4-8a37758a026f · inbound

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention cites this paper.

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a48ec12d-9f72-41da-94b8-f208e36eb6d8 · inbound

Kwai Keye-VL-2.0 Technical Report cites this paper.

Kwai Keye-VL-2.0 Technical Report ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2540585a-dd82-44aa-9c22-21aa383415c9 · inbound

MMGist: A Comprehensive Multimodal Benchmark for 2027 cites this paper.

MMGist: A Comprehensive Multimodal Benchmark for 2027 ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0f0806fb-8a45-4f6e-80d4-a406a98866c3 · inbound

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity cites this paper.

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:19:04.778549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4f6d477b-d9a0-4c0e-9363-d00355a128cb · inbound

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models cites this paper.

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T05:01:29.035002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af62350-4877-4c2b-b949-36e3c2447264 · inbound

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition cites this paper.

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T02:55:23.411003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.