Mercury 3 Release - GPQA Diamond: leaderboard
Inception Mercury 3 release comparison (2026-10-19): three explicitly Medium-effort models, exact source image cells. Release-specific harness and task populations are otherwise unspecified; no pooling with official benchmark leaderboards or other efforts. GDPval uses native Elo, all other columns use percentage scores. Accuracy (%).
Metric: Accuracy (%). Source: www.inceptionlabs.ai. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Luna (Medium) | 86.36 | #59 (GPT-6 Luna) |
| 2 | Claude Haiku 5.5 (Medium) | 84.51 | #40 (Claude Haiku 5.5) |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=mercury-3-release-gpqa-diamond · How It Works · Data refreshed daily, snapshot 2026-10-21.