Benchmark Almanac

Veris FinAgent Arena v1.1

Gemini 4 Carbon 757.0 leads since November 2026
Not in model cards

Agents investigate bank alerts, read Treasury scans, and complete research requests. The index combines accuracy and repeatability across three benchmarks, then applies a cost penalty.

Veris ranks 12 models that completed all three benchmarks. Bank payroll sets the weights. AML receives 51%, and each research benchmark receives 24.5%.

Made by
Veris AI
Released
November 2026
Kind
Composite work indices
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Documents → Actions, Text
Interaction
Agentic
Environment
APIs and tools
Items from
Another benchmark
Run by
A host
Strongest model tested
Gemini 4 Carbon #3 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
12
Models scored on its own leaderboard

Gemini 4 Carbon leads with 757.0

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.

  1. 1 Gemini 4 Carbon 757.0
  2. 2 Gemini 4 Argon 718.0
  3. 3 Gemini 4 Hydrogen 718.0
  4. 4 Claude Opus 5.5 637.0
  5. 5 GPT-6.1 Sol 592.0
  6. 6 Claude Sonnet 5.5 548.0
  7. 7 DeepSeek V4.1 Flash 512.0
  8. 8 GLM-5.3-Flash 488.0
  9. 9 Kimi K3 481.0
  10. 10 Gemini 3.8 Flash 477.0
  11. 11 Grok 4.7 422.0
  12. 12 GPT-5.6 Terra 282.0

Source: Official Veris FinAgent Arena v1.1 leaderboard

#ModelScoreSettingDateSource
1 Gemini 4 Carbon 757.0 Gemini CLI Oct 2026 Official leaderboard
2 Gemini 4 Argon 718.0 Gemini CLI Sep 2026 Official leaderboard
3 Gemini 4 Hydrogen 718.0 Gemini CLI Nov 2026 Official leaderboard
4 Claude Opus 5.5 637.0 Claude Code Sep 2026 Official leaderboard
5 GPT-6.1 Sol 592.0 Codex Sep 2026 Official leaderboard
6 Claude Sonnet 5.5 548.0 Claude Code Sep 2026 Official leaderboard
7 DeepSeek V4.1 Flash 512.0 Pi Sep 2026 Official leaderboard
8 GLM-5.3-Flash 488.0 Pi Aug 2026 Official leaderboard
9 Kimi K3 481.0 Pi Jul 2026 Official leaderboard
10 Gemini 3.8 Flash 477.0 Gemini CLI Sep 2026 Official leaderboard
11 Grok 4.7 422.0 Grok CLI Sep 2026 Official leaderboard
12 GPT-5.6 Terra 282.0 Codex Jul 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: AML Bench, TreasuryQA Bench and FinDesk-Bench. Each ranks models on one part of the test. Gemini 4 Carbon leads 2 of them, and Gemini 4 Hydrogen leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

AML Bench

12 models we track have a score here.

  1. 1 Gemini 4 Carbon 694.9
  2. 2 GPT-6.1 Sol ↑3 694.7
  3. 3 Gemini 4 Argon ↓1 676.1
  4. 4 Claude Sonnet 5.5 ↑2 668.1
  5. 5 GLM-5.3-Flash ↑3 663.3
  6. 6 Gemini 4 Hydrogen ↓3 662.0
  7. 7 Grok 4.7 ↑4 653.0
  8. 8 Claude Opus 5.5 ↓4 652.6
  9. 9 Kimi K3 649.0
  10. 10 DeepSeek V4.1 Flash ↓3 620.6

Number one over time

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

Google DeepMind
Own leaderboard 1 leader

Source: Official Veris FinAgent Arena v1.1 leaderboard

Scores over time

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
200 400 600 800 2027 200 400 600 800 2027

Source: Official Veris FinAgent Arena v1.1 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 Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 models we track.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Hydrogen.
  • Pass Frontier models 5 of the top 10 have a score, led by Gemini 4 Carbon (#3).
  • Note Headroom Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on veris.ai: 12 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