Aiera Leaderboard - Research Score: leaderboard
Aiera Leaderboard: models answer proprietary institutional-finance research questions through a client-side tool loop connected to Aiera's MCP server (filings, transcripts, research), best of three. The Aiera Research Score is the equal-weight mean of the Facts, Grounding and Depth axes; 0-100, higher is better.
Metric: Aiera Research Score (0-100). Source: huggingface.co. Saturation forecast: Around February 2027. 40 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 | 88.74 | #10 |
| 2 | Claude Opus 5 | 87 | #16 |
| 3 | Kimi K3 | 86.57 | #35 |
| 4 | Claude Fable 5 | 86.1 | #20 |
| 5 | GPT-5.6 Sol | 84.07 | #22 |
| 6 | Claude Opus 4.7 | 83.6 | #51 |
| 7 | Claude Opus 4.8 | 82.63 | #39 |
| 8 | MiniMax-M3 | 81.53 | #151 |
| 9 | GPT-5.6 Terra | 80.83 | #40 |
| 10 | GPT-5.5 | 80.73 | #33 |
| 11 | DeepSeek V4 Pro | 80.07 | #112 |
| 12 | Kimi K2.7 Code | 79.17 | #95 |
| 13 | Kimi K2.6 | 79.1 | #113 |
| 14 | GPT-5.6 Luna | 76.33 | #79 |
| 15 | Claude Sonnet 4.6 | 76.1 | #94 |
No result here: #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=aiera-leaderboard-research-score · How It Works · Data refreshed daily, snapshot 2026-11-05.