Benchmark Almanac

Questflow Finance Benchmark

GPT-6.1 Terra 100% leads since October 2026
Not in model cards

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
Language
English
In and out
Text, Documents, Tables → Text, Actions
Interaction
Agentic
Environment
APIs and tools
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
Claude Opus 5.5 #5 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
11
Models scored on its own leaderboard

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. 1 GPT-6.1 Terra 100%
  2. 2 MiMo-V2.6 Flash 99.4%
  3. 3 DeepSeek V4.1 Flash 97.7%
  4. 4 Claude Opus 5.5 97.7%
  5. 5 Kimi K3.1 Pro 97.7%
  6. 6 Qwen3.8 Flash 97.2%
  7. 7 MiniMax-M3.1-Flash 94.9%
  8. 8 Gemini 3.8 Flash 94.4%
  9. 9 GLM-5.3-Flash 89.9%
  10. 10 Grok 4.7 82.2%
  11. 11 MiniMax-M3 73.8%

Source: Official Questflow Finance Benchmark leaderboard

#ModelScoreSettingReleasedRun onSource
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 DeepSeek V4.1 Flash 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 Qwen3.8 Flash 97.2% Aug 2026 Sep 2026 Official leaderboard
7 MiniMax-M3.1-Flash 94.9% Oct 2026 Oct 2026 Official leaderboard
8 Gemini 3.8 Flash 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 MiniMax-M3 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. 1 Qwen3.8 Flash ↑5 100%
  2. 2 MiMo-V2.6 Flash 100%
  3. 3 GPT-6.1 Terra ↓2 100%
  4. 4 DeepSeek V4.1 Flash ↓1 97.7%
  5. 5 Claude Opus 5.5 ↓1 97.7%
  6. 6 GLM-5.3-Flash ↑3 94%
  7. 7 MiniMax-M3.1-Flash 94%
  8. 8 Kimi K3.1 Pro ↓3 94%
  9. 9 Gemini 3.8 Flash ↓1 90.3%
  10. 10 MiniMax-M3 ↑1 81%

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.

Xiaomi Corp OpenAI Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.02 $0.05 $0.10 $0.20 $0.50 $1.00 Cost per task, log scale GPT-6.1 Terra MiMo-V2.6 Flash 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra

Source: Official Questflow Finance Benchmark leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.1 Terra 100% $0.05
MiMo-V2.6 Flash 99.4% $0.01
DeepSeek V4.1 Flash 97.7% $0.13
Claude Opus 5.5 97.7% $0.91
Kimi K3.1 Pro 97.7% $0.26
Qwen3.8 Flash 97.2% $0.03
MiniMax-M3.1-Flash 94.9%
Gemini 3.8 Flash 94.4% $0.16
GLM-5.3-Flash 89.9% $0.02
Grok 4.7 82.2% $0.29
MiniMax-M3 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.

Xiaomi Corp OpenAI
Own leaderboard Passed 85% in Oct 2026, by MiMo-V2.6 Flash

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-6.1 Terra Qwen3.8 Flash GLM-5.3-Flash MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-6.1 Terra GLM-5.3-Flash

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

All 637 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.

How we check