FINESSE-Bench - Trading Derivatives: leaderboard

FINESSE-Bench Trading Derivatives tests financial knowledge with 544 numerical and short-answer tasks on options, put-call parity, Greeks, hedging, pricing and futures strategies 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 544 Trading_derivatives numerical and short-answer tasks on options, put-call parity, Greeks, hedging, pricing and futures strategies 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

#ModelSettingScoreOverall rank
1Kimi K2.586.58#272
2GPT-5.2Medium85.11#190
3Qwen 3.5 Plus (2026-02-15)83.64#196
4Qwen 3.5 397B A17B81.25#270
5Qwen 3.5 122B A10B80.51#350
6GLM-580.51#276
7GLM-4.779.23#383
8Claude Sonnet 4.6Medium78.49#179
9DeepSeek V3.277.39#425
10Qwen 3 235B A22B 2507 (Thinking)76.84#471
11DeepSeek R1 052876.1#432
12Qwen 3.5 35B A3B75.55#494
13Qwen 3.5 27B75.18#380
14GPT-5.4Medium75.18#138
15Qwen 3.5 Flash (02-23)74.26#525

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=finesse-bench-trading-derivatives · How It Works · Data refreshed daily, snapshot 2026-11-22.