Samaya AI, 2026

FrontierFinance

Open-ended investment research questions across six use cases: screening, company research, sector and macro, data extraction, earnings and events, and catalyst monitoring. Answers are scored against expert-written, source-attributed rubrics.

Best reported

58.9

Samaya SterlingSamaya AI

rubrics qualification rate %

Official board, 28 Oct 2026

About this benchmark

Size
220 queries, 11,543 rubric items
Public split
All 220 queries and rubrics, on Hugging Face (gated with automatic approval; you agree not to reshare)
Grading
An LLM judge panel decides each rubric item (majority vote, first judge breaks ties). Recommended judges are Claude Sonnet 4.6, Gemini 3.1 Pro and GPT 5.4. Headline metric is the rubrics qualification rate.
Licence
CC-BY-4.0 (data); Apache-2.0 (grader code)
Submission
Not stated
Products allowed
Yes
Latest version
2026-10-28
What it does not cover
No trade execution, portfolio outcomes or advice-safety checks.

Results

10 models
Leaderboard

Each score shows who reported it: the benchmark's authors (quoted from their paper), the benchmark's official board, or Moneda (run with the benchmark's own grader and rules). We do not copy other aggregators.

Best value: Samaya Sterling, 58.9 at $0.610 per question (cheapest within 5% of the top score)

FrontierFinance: score vs cost

Score against cost per test. Up and to the left is better.

Updated 28 Oct 2026

Y: rubrics qualification rate %X: Cost per test (USD)Showing 10 models
FrontierFinance: score vs cost10 models. Frontier: Samaya Sterling.5055$0$2$4$6EfficientInefficient↑ Best performance← Lowest costCost per test (USD)Samaya Sterling: 58.9 rubrics qualification rate %, $0.61 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Samaya SterlingLegacy Samaya System (high effort): 56 rubrics qualification rate %, $1.81 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Legacy Samaya System (high effort)Claude Fable 5.1 · Finance Agent v2: 55.9 rubrics qualification rate %, $6.89 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Fable 5.1 · Finance Agent v2Muse Spark Open · Finance Agent v2: 53.7 rubrics qualification rate %, $1.38 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Muse Spark Open · Finance Agent v2Legacy Samaya System: 52.9 rubrics qualification rate %, $0.93 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Legacy Samaya SystemMuse Wonder 1.0 · Finance Agent v2: 52.6 rubrics qualification rate %, $3.35 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Muse Wonder 1.0 · Finance Agent v2Claude Opus 5.5 · Finance Agent v2: 50.9 rubrics qualification rate %, $1.87 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Opus 5.5 · Finance Agent v2Gemini 3.8 Flash · Finance Agent v2: 50 rubrics qualification rate %, $1.21 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Gemini 3.8 Flash · Finance Agent v2Claude Fable 5 · Finance Agent v2: 49.2 rubrics qualification rate %, $4.06 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Fable 5 · Finance Agent v2GPT 5.6 Sol · Finance Agent v2: 46.8 rubrics qualification rate %, $3.03 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) GPT 5.6 Sol · Finance Agent v2FrontierFinance: score vs cost10 models. Frontier: Samaya Sterling.5055$0.5$1$2$5$10EfficientInefficient↑ Best performance← Lowest costCost per test (USD)Samaya Sterling: 58.9 rubrics qualification rate %, $0.61 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Samaya SterlingLegacy Samaya System (high effort): 56 rubrics qualification rate %, $1.81 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Legacy Samaya System (high effort)Claude Fable 5.1 · Finance Agent v2: 55.9 rubrics qualification rate %, $6.89 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Fable 5.1 · Finance Agent v2Muse Spark Open · Finance Agent v2: 53.7 rubrics qualification rate %, $1.38 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Muse Spark Open · Finance Agent v2Legacy Samaya System: 52.9 rubrics qualification rate %, $0.93 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) Legacy Samaya SystemMuse Wonder 1.0 · Finance Agent v2: 52.6 rubrics qualification rate %, $3.35 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Muse Wonder 1.0 · Finance Agent v2Claude Opus 5.5 · Finance Agent v2: 50.9 rubrics qualification rate %, $1.87 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Opus 5.5 · Finance Agent v2Gemini 3.8 Flash · Finance Agent v2: 50 rubrics qualification rate %, $1.21 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Gemini 3.8 Flash · Finance Agent v2Claude Fable 5 · Finance Agent v2: 49.2 rubrics qualification rate %, $4.06 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026)Claude Fable 5 · Finance Agent v2GPT 5.6 Sol · Finance Agent v2: 46.8 rubrics qualification rate %, $3.03 per test (Samaya FrontierFinance leaderboard, Avg. cost per query, 28 Oct 2026) GPT 5.6 Sol · Finance Agent v2

FrontierFinance 2026-10-28

rubrics qualification rate %, higher is better. 10 models.

Updated 28 Oct 2026

  1. Samaya Sterling58.9
  2. Legacy Samaya System (high effort)56
  3. Claude Fable 5.1 · Finance Agent v255.9
  4. Muse Spark Open · Finance Agent v253.7
  5. Legacy Samaya System52.9
  6. Muse Wonder 1.0 · Finance Agent v252.6
  7. Claude Opus 5.5 · Finance Agent v250.9
  8. Gemini 3.8 Flash · Finance Agent v250
  9. Claude Fable 5 · Finance Agent v249.2
  10. GPT 5.6 Sol · Finance Agent v246.8

FrontierFinance: cost

cost per test item (USD), lower is better. 10 models.

Updated 28 Oct 2026

  1. Samaya Sterling0.610
  2. Legacy Samaya System0.930
  3. Gemini 3.8 Flash · Finance Agent v21.2
  4. Muse Spark Open · Finance Agent v21.4
  5. Legacy Samaya System (high effort)1.8
  6. Claude Opus 5.5 · Finance Agent v21.9
  7. GPT 5.6 Sol · Finance Agent v23.0
  8. Muse Wonder 1.0 · Finance Agent v23.4
  9. Claude Fable 5 · Finance Agent v24.1
  10. Claude Fable 5.1 · Finance Agent v26.9

FrontierFinance 2026-10-28

rubrics qualification rate %, higher is better. 10 models.

Updated 28 Oct 2026

  1. 1Samaya Sterling58.9
  2. 2Legacy Samaya System (high effort)56
  3. 3Claude Fable 5.1 · Finance Agent v255.9
  4. 4Muse Spark Open · Finance Agent v253.7
  5. 5Legacy Samaya System52.9
  6. 6Muse Wonder 1.0 · Finance Agent v252.6
  7. 7Claude Opus 5.5 · Finance Agent v250.9
  8. 8Gemini 3.8 Flash · Finance Agent v250
  9. 9Claude Fable 5 · Finance Agent v249.2
  10. 10GPT 5.6 Sol · Finance Agent v246.8
FrontierFinance leaderboard (rubrics qualification rate %, higher is better)
1Samaya SterlingSamaya AI58.9Samaya harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
2Legacy Samaya System (high effort)Samaya AI56Samaya harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
3Claude Fable 5.1 · Finance Agent v2Anthropic55.9Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
4Muse Spark Open · Finance Agent v2Meta53.7Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
5Legacy Samaya SystemSamaya AI52.9Samaya harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
6Muse Wonder 1.0 · Finance Agent v2Meta52.6Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
7Claude Opus 5.5 · Finance Agent v2Anthropic50.9Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
8Gemini 3.8 Flash · Finance Agent v2Google50Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
9Claude Fable 5 · Finance Agent v2Anthropic49.2Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026
10GPT 5.6 Sol · Finance Agent v2OpenAI46.8Finance Agent v2 harnessSamaya leaderboard
Official board, reported 28 Oct 2026 · checked 1 Nov 2026

Last checked 1 Nov 2026. Something out of date or wrong? Send a correction.