AIME 2025
Harbor adapterAIME 2025: 30道AIME级数学题
Verified86%Math
- Samples
- 30
- Released
- 2025
- Scores
- 12
Grid-Bench
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
How to run
ltb · grid-bench
$ npm i -g lettokenburn-cli$ ltb bench info grid-bench
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
6 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 90.5 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| GPT-5.6 Sol | 81.6 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| GLM-5 | 62.4 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| GPT-5.4-mini | 56.1 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| Kimi K2.5 | 55.6 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
| MiniMax M2.5 | 52.4 | N/A | Independent | medium | Oct 15, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
Grid-Bench evaluates complete spatial state prediction. Each instance gives a language model an initial grid, explicit transition rules, and an ordered event history as text. The model predicts the complete final grid. Executable rules provide exact reference states, allowing both complete answers and individual cell values to be checked. Use the companion code repository to simulate, generate, and…