Questflow Finance Benchmark
Agents query financial filings and market data with a fixed set of tools. They calculate metrics, rank securities, and submit answers that software checks against frozen references.
Questflow ranks 11 models on 179 tasks. It publishes 40 examples with reference answers and per-model results. The score gives each task a pass or fail.
- Made by
- Questflow
- Released
- October 2026
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Law and finance
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
GPT-6.1 Terra leads with 100%
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
- 1 GPT-6.1 Terra 100%
- 2 MiMo-V2.6 Flash 99.4%
- 3
DeepSeek V4.1 Flash 97.7%
- 4 Claude Opus 5.5 97.7%
- 5 Kimi K3.1 Pro 97.7%
- 6
Qwen3.8 Flash 97.2%
- 7
MiniMax-M3.1-Flash 94.9%
- 8
Gemini 3.8 Flash 94.4%
- 9 GLM-5.3-Flash 89.9%
- 10 Grok 4.7 82.2%
- 11
MiniMax-M3 73.8%
Source: Official Questflow Finance Benchmark leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Terra | 100% | Oct 2026 | Oct 2026 | Official leaderboard | |
| 2 | MiMo-V2.6 Flash | 99.4% | Sep 2026 | Sep 2026 | Official leaderboard | |
| 3 | | 97.7% | Sep 2026 | Sep 2026 | Official leaderboard | |
| 4 | Claude Opus 5.5 | 97.7% | Sep 2026 | Sep 2026 | Official leaderboard | |
| 5 | Kimi K3.1 Pro | 97.7% | Oct 2026 | Oct 2026 | Official leaderboard | |
| 6 | | 97.2% | Aug 2026 | Sep 2026 | Official leaderboard | |
| 7 | | 94.9% | Oct 2026 | Oct 2026 | Official leaderboard | |
| 8 | | 94.4% | Sep 2026 | Sep 2026 | Official leaderboard | |
| 9 | GLM-5.3-Flash | 89.9% | Aug 2026 | Sep 2026 | Official leaderboard | |
| 10 | Grok 4.7 | 82.2% | Sep 2026 | Sep 2026 | Official leaderboard | |
| 11 | | 73.8% | Jun 2026 | Sep 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Financial Analysis and Market & Signal. Each ranks models on one part of the test. Qwen3.8 Flash leads Financial Analysis and GPT-6.1 Terra leads Market & Signal. Arrows show how far a model moved from its overall rank among the models we track.
Financial Analysis
11 models we track have a score here.
- 1
Qwen3.8 Flash ↑5 100%
- 2 MiMo-V2.6 Flash 100%
- 3 GPT-6.1 Terra ↓2 100%
- 4
DeepSeek V4.1 Flash ↓1 97.7%
- 5 Claude Opus 5.5 ↓1 97.7%
- 6 GLM-5.3-Flash ↑3 94%
- 7
MiniMax-M3.1-Flash 94%
- 8 Kimi K3.1 Pro ↓3 94%
- 9
Gemini 3.8 Flash ↓1 90.3%
- 10
MiniMax-M3 ↑1 81%
Market & Signal
11 models we track have a score here.
- 1 GPT-6.1 Terra 100%
- 2 MiMo-V2.6 Flash 99.2%
- 3 Kimi K3.1 Pro ↑2 99.2%
- 4
DeepSeek V4.1 Flash ↓1 97.6%
- 5 Claude Opus 5.5 ↓1 97.6%
- 6
Qwen3.8 Flash 96.1%
- 7
Gemini 3.8 Flash ↑1 96.1%
- 8
MiniMax-M3.1-Flash ↓1 95.3%
- 9 Grok 4.7 ↑1 90.6%
- 10 GLM-5.3-Flash ↓1 88.2%
The best score, 100%, costs $0.05 a task
Runs on the cost frontier score higher than any run that's cheaper. MiMo-V2.6 Flash comes within 0.6 points of the best for $0.01 a task, 4 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Questflow Finance Benchmark leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6.1 Terra | 100% | $0.05 | |||
| MiMo-V2.6 Flash | 99.4% | $0.01 | |||
| 97.7% | $0.13 | ||||
| Claude Opus 5.5 | 97.7% | $0.91 | |||
| Kimi K3.1 Pro | 97.7% | $0.26 | |||
| 97.2% | $0.03 | ||||
| 94.9% | |||||
| 94.4% | $0.16 | ||||
| GLM-5.3-Flash | 89.9% | $0.02 | |||
| Grok 4.7 | 82.2% | $0.29 | |||
| 73.8% | $0.06 |
2 models have held number one on the official leaderboard since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Questflow Finance Benchmark leaderboard
GLM-5.3-Flash on the official leaderboard passed 85% in August 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Questflow Finance Benchmark leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More 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%
- 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. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 11 models we track.
- Pass Newest score The newest is from October 2026, for GPT-6.1 Terra.
- Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is Claude Opus 5.5 (#5).
- Note Headroom Saturated. The best is 100%, past 85% since August 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on next.questflow.ai: 11 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.