This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2603.26653 · VIDEO REASONING BENCHMARK · SUBMITTED 30 MAR · 21:51 UTC · FRESHNESS STALE
ARXIV:2603.26653VIDEO REASONING BENCHMARKSUBMITTED 30 MAR · 21:51 UTCFRESHNESS STALEShaoxuan Li · Zhixuan Zhao · Hanze Deng · Zirun Ma · Shulin Tian · Zuyan Liu · +6 at arXiv
A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions.
Opportunity summary
Pain A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions.
Evidence 20 refs | 3 sources | 50% coverage
Blocker Evidence unverified
A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions. PerceptionComp is designed so that no single moment is sufficient: answering…
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence…
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops…
Video Reasoning Benchmark moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.
Continue into Read for claims, analysis, references, and neighboring papers.
mobile layout uses overflow-hidden min-w-0 break-wordsOpportunity summary
Score7.0Public score shown from the verified overall while the stale axis breakdown refreshesAnalysis summary
A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions.
Loading BUILD…
Paper Pack
10.48550/arXiv.2603.26653A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions.
Abstract
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic, spanning perceptual subtasks such as objects, attributes, relations, locations, actions, and events, and requiring skills including semantic recognition, visual correspondence, temporal reasoning, and spatial reasoning. The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18.97%) when rewatching is disallowed. State-of-the-art MLLMs also perform substantially worse on PerceptionComp than on existing benchmarks: the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting, while open-source models remain below 40%. These results suggest that perception-centric long-horizon video reasoning remains a major bottleneck, and we hope PerceptionComp will help drive progress in perceptual reasoning.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Parse run linkedA document parse run is attached to this paper.
Proof status
unverified20 refs; 3 sources; 50% coverage.
What was readable
Derived fallback: Estimated from adjacent evidence; not verified from source.
Viability
Time to MVP
Commercial
Export
Preparing verified analysis
Dimensions overall score 7.0
PROBLEM
A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple te...
METHOD
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence...
RESULT
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18....
WHY NOW
Video Reasoning Benchmark moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning.
This is explicitly stated in the first sentence of the abstract.
partial
PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic, spanning perceptual subtasks such as objects, attributes, relations, locations, actions, and events, and requiring skills including semantic recognition, visual correspondence, temporal reasoning, and spatial reasoning.
This is directly stated in the abstract, detailing the complexity of the benchmark.
partial
The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation.
The abstract provides the exact number of questions and videos, along with the diversity of domains.
partial
Human studies show that PerceptionComp requires substantial test-time thinking and repeated perception steps: participants take much longer than on prior benchmarks, and accuracy drops to near chance (18.97%) when rewatching is disallowed.
The abstract explicitly states the human performance metric under a specific condition.
partial
State-of-the-art MLLMs also perform substantially worse on PerceptionComp than on existing benchmarks: the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting, while open-source models remain below 40%.
The abstract provides a specific accuracy score for a state-of-the-art model.
partial
These results suggest that perception-centric long-horizon video reasoning remains a major bottleneck, and we hope PerceptionComp will help drive progress in perceptual reasoning.
This is a concluding statement in the abstract summarizing the implications of the results.
partial
All videos are sourced from real recordings rather than synthetic renderings; while some categories (e.g., game livestreams) are screen-captured, the videos still exhibit rich, naturally occurring dynamics and clutter that make the tasks challenging and practically relevant.
The text states that videos are sourced from real recordings and explains the rationale behind this choice.
partial
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning.
This is a direct statement from the abstract defining the benchmark.
partial
PerceptionComp is designed so that no single moment is sufficient: answering each question requires multiple temporally separated pieces of visual evidence and compositional constraints under conjunctive and sequential logic
This is a direct statement from the abstract describing the nature of the questions within the benchmark.
partial
The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains
This is a direct statement from the abstract providing quantitative details about the benchmark's content.
partial
accuracy drops to near chance (18.97%) when rewatching is disallowed.
This is a direct result reported in the abstract from human studies.
partial
the best model in our evaluation, Gemini-3-Flash, reaches only 45.96% accuracy in the five-choice setting
This is a direct result reported in the abstract regarding MLLM performance.
partial
Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.
Concepts
Methods
Materials
Markets
Competitors
A new benchmark for complex video reasoning that pushes the limits of current multimodal LLMs, creating an opportunity for specialized perception-centric AI solutions.
Segment
Video Reasoning Benchmark
Adoption evidence
No public code link in the paper record yet
Commercial read
7.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2603.26653 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.
Hacker News
Not indexed yet
Not indexed yet
Bluesky
Not indexed yet
Preview the source document here, or use the hero PDF action for a new tab.
Reference metadata is not materialized in the public index yet. The source PDF remains the authority; cache refresh is optional.
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Foundation
Extension
Commercially relevant
Conflicting
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
3/3 checks · 100%
Build Passport
Build passport pending - Proof Lab budget No verified cost estimate / $7.00 cap
status
missing
reason
passport_row_missing
proof status
unverified
cost/budget
No verified cost estimate
confidence low
next verification path
Build brief missing until Build Passport data exists.
Source missing: Build Passport payload.
Experiment plan missing until prototype path is available.
No prototype path attached.
Validation checklist missing until required assets, cost, and regulatory flags are verified.
No checklist artifact is attached to the Build Passport payload.
Derived signals show verified:false until source-backed receipts exist.
Evidence coverage
OpportunityKernel evidence_receipt
20 refs / 3 sources / 50% coverage
stale
Verify missing sources before using this as buyer proof. verified:false
Build readiness
BuildPassport EvidenceState
passport absent
stale
Run Proof Lab or inspect typed missing state. verified:false
Artifact maturity
GitHub and Hugging Face maturity payloads
No public artifact surface observed
stale
Open source artifacts or mark the gap as missing. verified:false
Technical feasibility
partial
Current read
Runnable path is not fully verified.
Evidence
No Build Passport payload attached.
Gaps
Next test
Run minimal reproduction from the Build Passport prototype path.
Market urgency
partial
Current read
Research evidence exists; buyer urgency still needs source proof.
Evidence
20 references, 3 sources, 50% evidence coverage.
Gaps
Next test
Collect buyer interview, deployment evidence, or cited demand signal.
Buyer clarity
missing
Current read
No budget owner is verified for this paper.
Evidence
Build tab has no CRM, procurement, or operator source.
Gaps
Next test
Map target operator, economic buyer, and procurement trigger.
Defensibility
missing
Current read
Defensibility signals are missing.
Evidence
No defensibility receipt attached.
Gaps
Next test
Refresh defensibility bars with source receipts.
Integration burden
missing
Current read
No public implementation surface observed.
Evidence
No GitHub or Hugging Face payload attached.
Gaps
Next test
Write integration checklist from prototype path and target workflow.
Capital intensity
missing
Current read
No observed cost estimate is verified.
Evidence
Cost passport has no observed_usd value.
Gaps
Next test
Run cost passport or mark the cost field not applicable.
Regulatory load
missing
Current read
No regulatory classification is attached.
Evidence
Build Passport ledger does not include regulatory flags.
Gaps
Next test
Classify regulatory flags before commercialization planning.
No named scientific founder assigned.
Paper authors are not treated as operators without consent.
People
No named person assigned.
Gaps
Next verification path
Prototype owner missing.
Build Passport does not name an implementer.
People
No named person assigned.
Gaps
Next verification path
Operator workflow not sourced.
No buyer or workflow interview attached.
People
No named person assigned.
Gaps
Next verification path
No GTM owner verified.
No CRM or outreach source attached.
People
No named person assigned.
Gaps
Next verification path
Regulatory need unclassified.
No clinical or regulatory source attached.
People
No named person assigned.
Gaps
Next verification path
ARTIFACTS
No public artifacts yet.
DEFENSIBILITY
Defensibility and confidence evidence pending.
WATCHTOWER
No verified watchtower monitor rows yet.
FORESIGHT
No prediction yet — minted on next Foresight batch.
OPPORTUNITYKERNEL CHANGES SINCE LAST VIEW
No verified OpportunityKernel changes since the last view.
COMPETITIVE LANDSCAPE UPDATES
No verified competitive landscape changes yet.
RELATED PAPER UPDATES
No verified related paper changes yet.
SIGNAL CANVAS HISTORY AND DELTAS
No Signal Canvas history deltas yet.
TIMELINE
Save this paper to start tracking momentum - commits, demos, and score changes appear here.
No tracked events yet.
Score trend will appear after multiple data points.
BUZZ
Buzz trend pending.