FINESSE-Bench - CFTe-like Level 1: leaderboard
FINESSE-Bench CFTe-like Level 1 tests financial knowledge with 781 multiple-choice questions on basic technical analysis (chart types, trends, support and resistance, moving averages) from FINESSE-Bench (2026). Answers are marked correct or incorrect by a GPT-5.2 judge against the reference; the score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the 781 CFTe-like Level 1 multiple-choice questions on basic technical analysis (chart types, trends, support and resistance, moving averages) of FINESSE-Bench; a GPT-5.2 judge marks each answer correct or incorrect against the reference; zero-shot, one fixed prompt per task type, temperature 0 where possible, reasoning configurations with medium effort where the model offers them; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 31 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.5 122B A10B | 86.81 | #346 | |
| 2 | Qwen 3.5 Plus (2026-02-15) | 86.81 | #194 | |
| 3 | Qwen 3.5 397B A17B | 85.53 | #264 | |
| 4 | Kimi K2.5 | 84.76 | #266 | |
| 5 | Claude Sonnet 4.6 | Medium | 84.64 | #173 |
| 6 | Qwen 3.5 27B | 84.38 | #375 | |
| 7 | GLM-4.7 | 84.25 | #380 | |
| 8 | Qwen 3 235B A22B 2507 (Thinking) | 83.99 | #466 | |
| 9 | GPT-5.2 | Medium | 83.99 | #185 |
| 10 | Qwen 3.5 Flash (02-23) | 83.1 | #557 | |
| 11 | Claude 3.7 Sonnet | Thinking | 82.59 | #470 |
| 12 | Llama 4 Maverick | 82.2 | #1110 | |
| 13 | GPT-5.4 | Medium | 82.2 | #135 |
| 14 | Qwen 3.5 35B A3B | 81.18 | #492 | |
| 15 | GLM-5 | 81.18 | #269 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=finesse-bench-cfte-like-level-1 · How It Works · Data refreshed daily, snapshot 2026-11-21.