Vending-Bench 2 leaderboard: which LLMs score highest
Vending-Bench 2 (running a vending business for a year (final money, $)) currently has scores for 19 models. The top score is $6,205 by Kimi K2.6; the median model scores $2,377 and the lowest scores $1.
| # | Model | Organisation | Vending-Bench 2 score | Cheapest input $/M | Source | Captured |
|---|---|---|---|---|---|---|
| 1 | Kimi K2.6 | Moonshot | $6,205 | $0.650 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 2 | GLM-5.1 | Z.ai (Zhipu AI) | $5,634 | $1.05 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 3 | Gemini 3 Pro Preview | Google DeepMind | $5,478 | $2.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 4 | Qwen 3.6 Plus (2026-04-02) | Alibaba | $5,115 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 5 | Kimi K2.7 Code | Moonshot | $5,083 | $0.671 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 6 | Claude Fable 5 (max) | Anthropic | $4,967 | $10.00 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 7 | grok-4-20 | xAI | $4,663 | $1.25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 8 | GLM-5 | Z.ai (Zhipu AI) | $4,432 | $0.600 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 9 | Qwen 3.6 Max (Preview) | Alibaba | $4,254 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 10 | GLM-4.7 | Z.ai (Zhipu AI) | $2,377 | $0.400 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 11 | MiniMax-M3 | MiniMax | $2,158 | $0.230 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 12 | Kimi K2.5 | Moonshot | $1,198 | $0.450 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 13 | grok-4-1-fast-reasoning | xAI | $1,107 | $0.200 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 14 | gemini-2.5-flash | Google DeepMind | $549 | $0.300 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 15 | Qwen3.5 Flash | Alibaba | $463 | $0.065 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 16 | Qwen3.5 27B | Alibaba | $202 | $0.195 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 17 | MiniMax-M2 | MiniMax | $161 | $0.300 | Epoch AI Benchmarking Hub | 2026-10-05 |
| 18 | Qwen3-Max-Instruct | Alibaba | $72 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
| 19 | Qwen3.5 Plus | Alibaba | $1 | — | Epoch AI Benchmarking Hub | 2026-10-05 |
Compare all benchmarks side by side on the live leaderboard →
Among the ten highest scorers, the cheapest listed API price belongs to GLM-4.7 at $0.400 per million input tokens (score $2,377).
What Vending-Bench 2 measures
Vending-Bench 2 measures running a vending business for a year (final money, $).
How to read these scores
Higher scores are better; the scale is specific to this benchmark, so compare models only on this board. Where a model is listed at several reasoning efforts, only its highest-effort row is shown. See the methodology for how rows are chosen.
Where the data comes from
Epoch AI Benchmarking Hub (CC BY 4.0). Scores were last captured 2026-10-05; the Captured column gives each row's date.