Skip to content

Benchmark

RSI Index

Coding benchmarks compare models on programming tasks. Scores are index points. Higher is better.

Models measured
4
Scores recorded
7
Sources
2
IQ weight
No weight published

Score distribution

50.6
Mean
56.3
Median
7.6
Std dev
41.9
10th percentile
57.9
90th percentile
41.7
Min
41.757.9
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.9
2GPT-5.6 SolOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.9
3GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.3
4GPT-5.6 TerraOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.3
5GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41.9
6GPT-5.6 LunaOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.41.9
7GPT 5.5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.41.7

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats