TIS-100 Bench: Signal Amplifier

Double each input value. A tiny arithmetic task exposes the cost of getting values to and from the working node.

In TIS-100 Bench, 16 LLMs each had one attempt at this TIS-100 puzzle, with 10 minutes to find a working program and keep improving it, without seeing the community leaderboard. 16 of 16 models solved it. No model found a new Pareto-frontier point beyond the community leaderboard.

16 / 16models solved it
84best LLM cycles (84 community)
0new frontier points

Records

ScoreCommunity bestBest LLMModel
Cycles8484Fable 5.1 Ties record
Nodes44DeepSeek V4.1 Flash Ties record
Instructions66DeepSeek V4.1 Flash Ties record

Community records from the community leaderboard when we froze it. A record counts only after fresh-game replay and 100,000 passing random tests.

Pareto frontier

Pareto explorer

Lower is better ↙
Loading interactive Pareto explorer…
Community leaderboardModel frontier pointNew frontier point
Select a point with the mouse or keyboard to inspect its scores and program.

Search over time

Loading puzzle trajectories…

Every model

ModelSolvedBest cyclesBest nodesBest instructionsNew frontier points
01Fable 5.1Yes8446—
02GLM-5.3Yes8446—
03GPT-6 AstraYes8446—
04GPT-6.1 SolYes8446—
05Gemini 3.8 FlashYes8446—
06Gemini 4 ArgonYes8446—
07Grok 4.7Yes8446—
08Haiku 5.5Yes8446—
09Kimi K3.1 ProYes8446—
10MiMo-V2.6-ProYes8446—
11Muse Spark 1.3Yes8446—
12Muse Wonder 1.0Yes8446—
13Opus 5.5Yes8446—
14Sonnet 5.5Yes8446—
15DeepSeek V4.1 FlashYes10346—
16GPT-6 LunaYes16046—

Best scores can come from different programs. New frontier points are not matched or beaten on all three scores by any community program.

Best model programs

These programs are in TIS-100 save format and released under the MIT License. All of this puzzle’s model programs are on GitHub and Hugging Face.

Fable 5.1 Fewest cycles

84 cycles · 5 nodes · 9 instructions10981.84-5-9.txt on GitHub

Fable 5.1 program running on 10981 in TIS-100
Node 1
MOV UP, DOWN
Node 4
MOV UP, ANY
Node 5
MOV LEFT, ACC
ADD ACC
MOV ACC, DOWN
Node 7
MOV UP, ACC
ADD ACC
MOV ACC, RIGHT
Node 8
MOV ANY, DOWN

Fable 5.1 Fewest nodes

108 cycles · 4 nodes · 16 instructions10981.108-4-16.txt on GitHub

Fable 5.1 program running on 10981 in TIS-100
Node 1
MOV UP, DOWN
Node 4
MOV UP, DOWN
MOV UP, DOWN
MOV UP, ACC
ADD ACC
MOV ACC, DOWN
Node 7
MOV UP, RIGHT
MOV UP, ACC
ADD ACC
MOV ACC, RIGHT
MOV UP, RIGHT
Node 8
MOV LEFT, ACC
ADD ACC
MOV ACC, DOWN
MOV LEFT, DOWN
MOV LEFT, DOWN

DeepSeek V4.1 Flash Fewest instructions

160 cycles · 4 nodes · 6 instructions10981.160-4-6.txt on GitHub

DeepSeek V4.1 Flash program running on 10981 in TIS-100
Node 1
MOV UP, ACC
ADD ACC
MOV ACC, DOWN
Node 4
MOV UP, DOWN
Node 7
MOV UP, RIGHT
Node 8
MOV LEFT, DOWN