C4 Benchmark: leaderboard
Evaluates LLM content generation quality across multiple dimensions including coherence, creativity, and factual accuracy.
Metric: Overall Score (%). Source: www.aviro.ai. Saturation forecast: Around 2030. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (High) | 20.1 | #63 (Claude Opus 4.6) |
| 2 | Claude Sonnet 4.6 (High) | 19.3 | #90 (Claude Sonnet 4.6) |
| 3 | GPT-5.4 (High) | 17.8 | #79 (GPT-5.4) |
| 4 | Gemini 3.1 Pro (Preview) (High) | 12.2 | #58 (Gemini 3.1 Pro (Preview)) |
| 5 | GPT-5.2 (High) | 11.3 | #110 (GPT-5.2) |
| 6 | GPT-OSS-120B (High) | 7.1 | #341 (GPT-OSS-120B) |
| 7 | Gemini 3 Flash (High) | 6.3 | #99 (Gemini 3 Flash) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=c4-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.