LLMsPark - Nim Game: leaderboard
Models choose legal removals in the strategic game Nim, planning moves to reach a winning outcome under the primary rules. Native Elo rating with initial 1000 and K=32, reported to two decimal places in primary Table 1; no finite theoretical bound is asserted.
Metric: Elo rating (initial 1000, K=32). Source: llmsparks.github.io. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 1245.87 | #438 |
| 2 | Dolly V2 12B | 1180.35 | #1620 |
| 3 | GPT-3.5 Turbo | 1155.5 | #865 |
| 4 | Baichuan-7B | 945.25 | #1527 |
| 5 | ChatGLM2 6B | 920.05 | #1498 |
| 6 | Baichuan2-7B-Chat | 875.4 | #1420 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llmspark-nim-game · How It Works · Data refreshed daily, snapshot 2026-10-20.