Kaggle Enterprise Ops (IBM) — leaderboard
Metric: Avg Score (%). Source: www.kaggle.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 6374 |
| 2 | O3 | 5962 |
| 3 | GPT-5 | 5954 |
| 4 | Claude Opus 4.5 | 5939 |
| 5 | GPT-5.1 | 5905 |
| 6 | Gemini 2.5 Flash | 5860 |
| 7 | Claude Sonnet 4.5 | 5503 |
| 8 | Gemini 2.5 Pro | 5464 |
| 9 | Claude Haiku 4.5 | 5195 |
| 10 | Grok 4.1 Fast (Reasoning) | 5180 |
| 11 | Mistral Small 3.1 | 4042 |
| 12 | DeepSeek R1 | 2623 |
Interactive version: theaggregate.ai/benchmark?slug=kaggle-enterprise-ops-ibm · How the rankings work · Data refreshed daily, snapshot 2026-07-22.