LLMs Play Zachtronics' TIS-100
A benchmark study gave 16 LLMs the TIS-100 programming game and its manual, withholding the community leaderboard, and asked them to improve their solutions.
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourcetis-100.wincon.dev
- Discovery linkHacker News
- Linked in sourceTIS-100
- Linked in sourcecommunity leaderboard
- Linked in sourceall 47 puzzles in the game, plus eight community tournament puzzles
- Linked in sourcehypervolume
- Linked in sourceTIS-100-CXX simulator
- Linked in sourceUndecimal Twin Rounder SPEC44149538
- Linked in sourceIntersection Identifier SPEC64160260
- Linked in sourceError: 8 SPEC79324720
- Linked in sourceSignal Multiplier 43786
- Linked in sourceSignal Window Filter 60099
- Linked in sourceT31 Node Emulator NEXUS.23.727.9
- Linked in sourceSequence Mode Calculator NEXUS.09.904.9
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Open full article view →- Community discussion+5
- Fetched source page+30
- No editor link review+0
- Community link+0
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
A benchmark study gave 16 LLMs the TIS-100 programming game and its manual, withholding the community leaderboard, and asked them to improve their solutions. Models ran 47 game puzzles plus eight tournament puzzles, one scored attempt each. The page reports 133 new frontier points across 18 of 55 puzzles, 18 of which beat community records outright, with Opus 5.5 and GPT-6 Astra leading. Scoring required fresh-game replay and 100,000 passing tests on an independent simulator.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; results come from a single scored attempt per model per puzzle (pass@1) and the authors' own harness.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; results come from a single scored attempt per model per puzzle (pass@1) and the authors' own harness.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Opus 5.5 and GPT-6 Astra both solved all 55 puzzles and each found new frontier points on 11 puzzles.
Source: tis-100.wincon.dev ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe study reports 133 new frontier points, of which 18 beat a community record outright.
Source: tis-100.wincon.dev ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseCost did not track quality: GPT-6.1 Sol scored 75.6 record proximity at about $0.75 per puzzle versus Opus 5.5 at 77.2 for $5.08.
Source: tis-100.wincon.dev ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; results come from a single scored attempt per model per puzzle (pass@1) and the authors' own harness.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
The study offers a verifiable, testable setting for measuring LLM program optimization beyond pass/fail correctness, separating solving from optimizing and tracking cost against quality.
Limits and open questions
Source claims not independently checked; results come from a single scored attempt per model per puzzle (pass@1) and the authors' own harness.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →