New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
FullStackBench benchmark
AI model leaderboard for the FullStackBench benchmark. Compare how large language models score on FullStackBench, see the full ranking, and understand what this AI benchmark measures. MiniMax-M1-80k currently leads with 68.3%. Full-stack code generation benchmark covering 11 real-world programming domains.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | MiniMax-M1-80k | MiniMax | 68.3% | 16 samples | official ↗ |
| #2 | MiniMax-M1-40k | MiniMax | 67.6% | 16 samples | official ↗ |
| #3 | Ling-1T | Ant Group | 56.55% | pass@1 | official ↗ |
| #4 | DeepSeek-V3.1-Terminus | DeepSeek | 55.48% | non-thinking-cited-ling-1t | official ↗ |
| #5 | Kimi K2 | Moonshot | 54% | instruct-0905-cited-ling-1t | official ↗ |
| #6 | GPT-5 | OpenAI | 50.92% | main-cited-ling-1t | official ↗ |
| #7 | gemini-2.5-pro | Google DeepMind | 48.19% | lowthink-cited-ling-1t | official ↗ |
Frequently asked questions about FullStackBench
What is the FullStackBench benchmark?
Full-stack code generation benchmark covering 11 real-world programming domains.
How is the FullStackBench benchmark scored?
FullStackBench is scored using the pass@1 (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on FullStackBench?
As of the latest reported scores on GenAIList, MiniMax-M1-80k achieves the highest result on FullStackBench with a score of 68.3%.
Is a higher FullStackBench score better?
Yes. On FullStackBench a higher score indicates better performance, so models near the top of the leaderboard are the strongest.