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
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.9 |
| 2 | GPT-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 |
| 3 | GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.3 |
| 4 | GPT-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 |
| 5 | GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.9 |
| 6 | GPT-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 |
| 7 | GPT 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