Market-Bench: 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 cumulative profit in simulation currency units, which can be negative; higher is better.
Metric: Cumulative profit (simulation currency units, signed; each agent starts with 22,500 in funds); 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 Pro | 36589 | #276 |
| 2 | Gemini 2.5 Flash | 26104 | #463 |
| 3 | O3 | 13368 | #237 |
| 4 | Claude Sonnet 4.5 | 10619 | #261 |
| 5 | GPT-4o | 7619 | #751 |
| 6 | Phi-4 | 7565 | #1931 |
| 7 | Qwen 2.5 VL 72B Instruct | 3402 | #841 |
| 8 | Market-Bench Llama 3.1 70B (checkpoint unspecified) | 2444 | |
| 9 | QwenLong-L1-32B | 2242 | #1881 |
| 10 | Market-Bench Qwen2.5 32B (checkpoint unspecified) | 1815 | |
| 11 | Market-Bench Gemma 3 27B (checkpoint unspecified) | 1481 | |
| 12 | Qwen 2.5 VL 32B Instruct | 1409 | #1062 |
| 13 | ERNIE 4.5 300B A47B | 1360 | #1122 |
| 14 | Market-Bench InternLM2.5 20B (checkpoint unspecified) | 1154 | |
| 15 | InternLM3-8B-Instruct | 1022 | #2703 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=market-bench · How It Works · Data refreshed daily, snapshot 2026-11-21.