# grok-4 finance AI benchmark results

Every finance benchmark score for grok-4 by xAI: 5 benchmarks, each with its rank, metric and source date. Scores are never combined across benchmarks.

## Scores

| Benchmark | Rank | Score | Metric | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FinSearchComp](https://benchmarks.finance/benchmarks/finsearchcomp/) | 1 of 11 | 68.9 | Global subset average accuracy % | Paper Table 5 | 16 Sept 2025 |
| [Market-Bench](https://benchmarks.finance/benchmarks/afterquery-market-bench/) | 1 of 10 | 443.2 | mean MAE | marketbench.ai leaderboard | date not stated |
| [FinDeepResearch](https://benchmarks.finance/benchmarks/findeepresearch/) | 4 of 10 | 37.3 | overall accuracy score (0-100) | OpenFinArena leaderboard | 15 Oct 2025 |
| [Reasoning Models Ace the CFA Exams (CFA mock-exam evaluation)](https://benchmarks.finance/benchmarks/cfa-reasoning-models-ace/) | 4 of 6 | 94.8 | Level I accuracy % | Paper Table 5 | 9 Dec 2025 |
| [LiveTradeBench](https://benchmarks.finance/benchmarks/livetradebench/) | 7 of 10 | 4.3 | cumulative return % | Paper Table 2 | 5 Nov 2025 |

Source: https://benchmarks.finance/models/grok-4/

Created and maintained by Moneda.