Benchmark Almanac

QF-Bench

GPT-5.5 61.7% leads since May 2026
Not in model cards

Agents write and run code for 87 quantitative finance tasks in a network-isolated sandbox with real data. Tasks cover derivatives pricing, fixed income, credit, risk, factor research, backtesting and market microstructure. More than 3,300 assertions check numeric outputs against finance rules such as no-arbitrage bounds and put-call parity. Scored by pass@1 over three runs.

Tasks run on the Harbor framework. The draft paper reports 42 models over 10,962 runs, but the public leaderboard shows 9 agent and model pairs dated May 7th, 2026. The authors are anonymous. About 60 GitHub stars.

Released
May 2026
Kind
Finance
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-5.5 #20 on the capability index
Last model added
April 2026
Scores refreshed
November 12th, 2026
9
Models scored on its own leaderboard

GPT-5.5 leads with 61.7% among models released by April 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 61.7 GPT-5.5
  2. 61.2 Claude Opus 4.7
  3. 60.8 GPT-5.3 Codex
  4. 59.2 Claude Opus 4.6
  5. 57.5 GPT-5.4
  6. 57.1 GPT-5.4 Mini
  7. 56.3 Claude Sonnet 4.6
  8. 46.2 Claude Sonnet 4.5
  9. 20.8 Claude Haiku 4.5
  1. 1 GPT-5.5 V11 CLI 61.7%
  2. 2 Claude Opus 4.7 V11 CLI 61.2%
  3. 3 GPT-5.3 Codex V11 CLI 60.8%
  4. 4 Claude Opus 4.6 V11 CLI 59.2%
  5. 5 GPT-5.4 V11 CLI 57.5%
  6. 6 GPT-5.4 Mini V11 CLI 57.1%
  7. 7 Claude Sonnet 4.6 V11 CLI 56.3%
  8. 8 Claude Sonnet 4.5 V11 CLI 46.2%
  9. 9 Claude Haiku 4.5 V11 CLI 20.8%

Source: Official QF-Bench leaderboard

#ModelScoreSettingDateSource
1 GPT-5.5 61.7% V11 CLI, codex-cli Apr 2026 Official leaderboard
2 Claude Opus 4.7 61.2% V11 CLI, claude-code Apr 2026 Official leaderboard
3 GPT-5.3 Codex 60.8% V11 CLI, codex-cli Feb 2026 Official leaderboard
4 Claude Opus 4.6 59.2% V11 CLI, claude-code Feb 2026 Official leaderboard
5 GPT-5.4 57.5% V11 CLI, codex-cli Mar 2026 Official leaderboard
6 GPT-5.4 Mini 57.1% V11 CLI, codex-cli Mar 2026 Official leaderboard
7 Claude Sonnet 4.6 56.3% V11 CLI, claude-code Feb 2026 Official leaderboard
8 Claude Sonnet 4.5 46.2% V11 CLI, claude-code Sep 2025 Official leaderboard
9 Claude Haiku 4.5 20.8% V11 CLI, claude-code Oct 2025 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since May 2026
GPT-5.5 61.7%

Source: Official QF-Bench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 GPT-5.3 Codex Claude Sonnet 4.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 Claude Sonnet 4.5

Source: Official QF-Bench leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 179 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items. Solar Pro 4 77.5%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. Solar Pro 4 93.2%