Reific Environments - Personal Agents: leaderboard
Reific's Personal Agents environments evaluate agents on personal work as new records arrive. Records arrive over time; agents read, run code, ask people and act with tools. The score is mean graded reward across environments in the family, not a task pass rate. The shared source protocol uses high reasoning and fresh repeated trials; numeric checks are deterministic, other outputs average two judges. Exact endpoints, numeric budgets and judge identities remain source-scoped and unreported.
Metric: Mean graded reward (%). Source: reific.co. Saturation forecast: Rough model projection: around 2026. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon (Reific Run: native=Gemini%204%20Argon; cfg=894138d508356a5e) | 31.6 | |
| 2 | Claude Opus 5.5 (Reific Run: native=Claude%20Opus%205.5; cfg=ba20783f598bfef7) | 27 | |
| 3 | Claude Sonnet 5.5 (Reific Run: native=Claude%20Sonnet%205.5; cfg=ccd0a9d2ec8c2b92) | 17.4 | |
| 4 | DeepSeek V4.1 Flash (Reific Run: native=DeepSeek-V4.1-Flash; cfg=32c7cd55c9b9eae5) | 15.9 | |
| 5 | GPT-6 Astra (Reific Run: native=GPT-6%20Astra; cfg=ae3b2e98cfafdb96) | 14.8 | |
| 6 | GLM-5.3 (Reific Run: native=GLM-5.3; cfg=ea5f1954dfb6956d) | 14.7 | |
| 7 | Gemini 3.8 Flash (Reific Run: native=Gemini%203.8%20Flash; cfg=01c08c6866549c92) | 13.7 | |
| 8 | GPT-6.1 Sol (Reific Run: native=GPT-6.1%20Sol; cfg=a8a089cd5143b78d) | 11.9 | |
| 9 | Qwen3.8-Flash-Next (Reific Run: native=Qwen3.8-Flash-Next; cfg=8dafc68734e9a2d0) | 11.7 | |
| 10 | DeepSeek V4 Pro (Reific Run: native=DeepSeek-V4-Pro; cfg=9a67942d374b3267) | 11.6 |
Interactive version: theaggregate.ai/benchmark?slug=reific-environments-personal-agents · How It Works · Data refreshed daily, snapshot 2026-11-05.