FinEval 6.0 - Agent Application: leaderboard
Metric: Score (0-100). Source: github.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 32B (Thinking) | 84.62 |
| 2 | Qwen 3 32B | 83.05 |
| 3 | GPT-4o | 82.15 |
| 4 | Qwen 3 30B A3B | 81.53 |
| 5 | Llama 3.3 70B | 78.48 |
| 6 | GLM-Z1-32B-0414 | 74.52 |
| 7 | InternLM3-8B-Instruct | 72.51 |
Interactive version: theaggregate.ai/benchmark?slug=fineval-6-0-agent-application · How It Works · Data refreshed daily, snapshot 2026-09-26.