Market-Bench - Bid Efficiency: leaderboard
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. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 0.8 |
| 2 | Gemini 2.5 Pro | 0.79 |
| 3 | O3 | 0.7 |
| 4 | GPT-4o | 0.45 |
| 5 | ERNIE 4.5 300B A47B | 0.42 |
| 6 | Claude Sonnet 4.5 | 0.41 |
| 7 | Phi-4 | 0.39 |
| 8 | Qwen 2.5 VL 72B Instruct | 0.32 |
| 9 | InternLM3-8B-Instruct | 0.28 |
| 10 | DeepSeek V3.2 | 0.24 |
| 11 | Qwen 2.5 VL 32B Instruct | 0.2 |
Interactive version: theaggregate.ai/benchmark?slug=market-bench-bid-efficiency · How It Works · Data refreshed daily, snapshot 2026-10-07.