Market-Bench - Bid Efficiency: leaderboard
Market-Bench (2026) places LLM-driven retailer agents together in one simulated supply-chain market where they bid for stock in budget-constrained auctions, set prices and write slogans for persona-driven buyers; values are means over 10 runs of a 6-step simulation at temperature 0. This board is the won share of the quantity bid times the base value of the won goods over the price paid; higher is better.
Metric: Bid efficiency (won share of bid quantity times base value of won goods over the amount paid; 0 or more); all 20 models compete as retailer agents in one simulated supply-chain market (sealed-bid procurement auctions, retail pricing and slogans; 6 steps, temperature 0), mean over 10 runs; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 0.795 | #466 |
| 2 | Gemini 2.5 Pro | 0.792 | #280 |
| 3 | O3 | 0.699 | #242 |
| 4 | GPT-4o | 0.45 | #754 |
| 5 | Market-Bench InternLM2.5 20B (checkpoint unspecified) | 0.441 | |
| 6 | ERNIE 4.5 300B A47B | 0.418 | #1130 |
| 7 | Claude Sonnet 4.5 | 0.411 | #267 |
| 8 | Phi-4 | 0.386 | #1951 |
| 9 | Qwen 2.5 VL 72B Instruct | 0.318 | #849 |
| 10 | Market-Bench Gemma 3 27B (checkpoint unspecified) | 0.296 | |
| 11 | InternLM3-8B-Instruct | 0.28 | #2714 |
| 12 | DeepSeek V3.2 | 0.237 | #425 |
| 13 | ERNIE 4.5 21B A3B | 0.216 | #2022 |
| 14 | Qwen 2.5 VL 32B Instruct | 0.197 | #1065 |
| 15 | Market-Bench Llama 3.1 70B (checkpoint unspecified) | 0.195 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=market-bench-bid-efficiency · How It Works · Data refreshed daily, snapshot 2026-11-22.