ISA-Bench - Human Resource Machine: leaderboard
Metric: Tasks solved (%; share of the 36 Human Resource Machine tasks (an accumulator machine with a small instruction set) whose program passes every verification case in the game's own parser, virtual machine and verifier; up to five attempts with parse, runtime or per-test execution feedback; Ollama default builds, temperature 0.7, 4,096 output tokens). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | ISA-Bench Gemma-4 31B (Thinking, Ollama build) | 88.89 |
| 2 | ISA-Bench Phi-4-Reasoning (Ollama build) | 55.56 |
| 3 | ISA-Bench Qwen3 32B (Thinking, Ollama build) | 44.44 |
| 4 | ISA-Bench Qwen3-Coder 30B (Ollama build) | 38.89 |
| 5 | ISA-Bench Qwen3 14B (Thinking, Ollama build) | 36.11 |
| 6 | ISA-Bench DeepSeek-R1 32B (Ollama build) | 36.11 |
| 7 | ISA-Bench Devstral-Small-2 (Ollama build) | 33.33 |
| 8 | ISA-Bench Qwen3 8B (Thinking, Ollama build) | 33.33 |
| 9 | ISA-Bench Qwen2.5-Coder 32B (Ollama build) | 19.44 |
| 10 | ISA-Bench Granite-4.1 8B (Ollama build) | 16.67 |
Interactive version: theaggregate.ai/benchmark?slug=isa-bench-human-resource-machine · How It Works · Data refreshed daily, snapshot 2026-09-26.