Team: Spektr-SQL

Affiliation: Amazon Ads - SpektrBot

Authors: Kishore Kumar, Scott Roberts, Desik Rengarajan, Ravi Shankar (Amazon Ads)

Submitted: June 15, 2026

Category: 4 (Combined Models — GPU + API)


Results

Dev (1531 questions) Test
Execution Accuracy 73.09% (1119/1531) 78.31% (1401/1789)

Per-Database Accuracy (Dev)

Database Accuracy Questions
superhero 90.7% 117/129
student_club 86.7% 137/158
codebase_community 76.1% 140/184
european_football_2 76.0% 98/129
debit_card_specializing 75.0% 48/64
california_schools 73.0% 65/89
financial 72.6% 77/106
toxicology 70.3% 102/145
card_games 64.7% 123/190
formula_1 64.9% 113/174
thrombosis_prediction 60.7% 99/163

Method Overview

Two-Phase Agentic Ensemble Pipeline:

Phase 1 (GPU): Fine-tuned Qwen3-30B-A3B MoE model generates 36 SQL candidates per question.

Phase 2 (API): Claude Sonnet 4.6 runs a multi-turn agentic verification loop with database exploration tools. If it disagrees with the FT, Claude Opus 4.6 acts as tiebreaker.


Resources

Component Specification
GPU 8× H100 80GB
GPU Model Qwen3-30B-A3B-Instruct-2507 (MoE, ~3B active)
API Models Claude Sonnet 4.6 + Claude Opus 4.6
Total Runtime ~8-10 hours
API Cost ~$200-250 (with prompt caching)
Column Meaning YES
External Knowledge YES
Self-Consistency Many (n=36)