Grok-3 mini
Grok-3 mini from xAI.
Shogo Agent Index
UnrankedNot ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
23
estimated
Long-horizon autonomy
33
estimated
Knowledge-work agents
20
estimated
Computer use
12
estimated
Security & context learning
23
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 58 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 17 | |
| DeepSWE | est. | 6% | predicted 15 | |
| FrontierSWE | est. | 5% | predicted 2 | |
| CursorBench | est. | 4% | predicted 21 | |
| GSO-Bench | est. | 4% | predicted 4 | |
| METR Time Horizons | est. | 10% | predicted 57 | |
| Vending-Bench 2 | est. | 6% | predicted 5 | |
| PostTrainBench | est. | 4% | predicted 14 | |
| APEX-Agents | est. | 8% | predicted 16 | |
| GDPval | est. | 7% | predicted 23 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 43 | |
| OSWorld 2.0 | est. | 6% | predicted 1 | |
| OSWorld | est. | 4% | predicted 27 | |
| Cybench | est. | 5% | predicted 32 | |
| CL-bench | est. | 5% | predicted 14 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 49.3% | source |
| ARC-AGI | Reasoning | 16.5% | source |
| ARC-AGI-2 | Reasoning | 0.4% | source |
| Fiction.LiveBench | Long context | 66.7% | source |
| GPQA Diamond | Reasoning | 76.3% | source |
| MATH Level 5 | Math | 90.9% | source |
| OTIS Mock AIME | Math | 77.8% | source |