LinAlg-Bench — leaderboard
Metric: 3Ã3 Overall Model Accuracy (%) (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 100 |
| 2 | O1 | 100 |
| 3 | DeepSeek V3 | 99.5 |
| 4 | GPT-5.2 | 98.2 |
| 5 | Mistral Large | 98.2 |
| 6 | Claude Sonnet 4.5 | 95.9 |
| 7 | Qwen 3 235B A22B | 92.7 |
| 8 | Qwen 2.5 72B Instruct | 91.8 |
| 9 | GPT-4o | 90.9 |
| 10 | Llama 3.3 70B Instruct | 87.3 |
Interactive version: theaggregate.ai/benchmark?slug=linalg-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.