C3-Bench — leaderboard
Metric: Aggregation (self-reported). Source: benchmarklist.com. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 5.72 |
| 2 | GPT-5.1 | 5.49 |
| 3 | Gemini 3 Flash (Preview) | 5.39 |
| 4 | Gemini 2.5 Pro | 5.23 |
| 5 | Gemini 2.5 Flash | 5.04 |
| 6 | GPT-4o | 4.95 |
| 7 | InternVL3-78B | 4.94 |
| 8 | GPT-5 Mini | 4.87 |
| 9 | InternVL3-38B | 4.72 |
| 10 | Llama 4 Scout | 4.71 |
| 11 | GPT-4o Mini | 4.65 |
| 12 | InternVL3.5-8B | 4.44 |
| 13 | InternVL3-8B | 4.1 |
Interactive version: theaggregate.ai/benchmark?slug=c3-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.