Visa Agentic Commerce Benchmark - Required Checks Completed: leaderboard
Visa Agentic Commerce Benchmark (Visa Research, October 2026 results snapshot, released November 5) evaluates whether a shopping assistant can uncover a customer's hidden requirements and select a suitable offer in a fixed simulated market, or correctly decline when nothing fits. Twenty-two models each complete 15 episodes three times, for 45 scored runs per model and 990 total. This series reports Required customer checks completed (%): native research-report share of required customer actions requested, such as consulting a partner or measuring a space; measured on applicable episodes. Reasoning effort, the exact third-party access service, customer/judge models and harness version are not reported; native model IDs preserve dated and preview variants. Announced tool/format limits count as failure. Nine unannounced-limit truncations were each replaced once; every replacement outcome counts. The separate public demo replays are not part of the scored pool.
Metric: Required customer checks completed (%): native research-report share of required customer actions requested, such as consulting a partner or measuring a space; measured on applicable episodes; October 2026 snapshot, higher is better. Source: www.visapaymentsfrontier.io. Saturation forecast: Rough model projection: around 2026. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=openai%2Fgpt-6-astra; effort=unreported; service=third-party) | 100 | |
| 2 | GPT-6.1 Sol (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=openai%2Fgpt-6.1-sol; effort=unreported; service=third-party) | 95.83 | |
| 3 | GPT-6 Luna (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=openai%2Fgpt-6-luna; effort=unreported; service=third-party) | 93.75 | |
| 4 | GPT-6.1 Terra (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=openai%2Fgpt-6.1-terra; effort=unreported; service=third-party) | 91.67 | |
| 5 | Claude Fable 5.1 (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=anthropic%2Fclaude-fable-5.1; effort=unreported; service=third-party) | 89.58 | |
| 6 | Gemini 4 Argon (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=google%2Fgemini-4-argon; effort=unreported; service=third-party) | 87.5 | |
| 7 | Muse Wonder (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=meta%2Fmuse-wonder; effort=unreported; service=third-party) | 87.5 | |
| 8 | Muse Spark 1.3 (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=meta%2Fmuse-spark-1.3; effort=unreported; service=third-party) | 87.5 | |
| 9 | GLM-5.3 (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=z-ai%2Fglm-5.3; effort=unreported; service=third-party) | 85.42 | |
| 10 | DeepSeek V4.1 Flash (1017) (Benchmark Sweep Run: Visa Commerce; snapshot=results-2026-11-03; source-model=deepseek%2Fdeepseek-v4.1-flash-1017; effort=unreported; service=third-party) | 85.42 |
Interactive version: theaggregate.ai/benchmark?slug=visa-agentic-commerce-benchmark-required-checks-completed · How It Works · Data refreshed daily, snapshot 2026-11-06.