Benchmark
Internal API instruction following (hard)
Instruction following benchmarks measure how closely models follow instructions. Scores are percentages.
All instruction following benchmarksScores from LLM Stats data.
- Models measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- 1.83
Score distribution
- 46.1%
- Mean
- 49.1%
- Median
- 11.4%
- Std dev
- 31.6%
- 10th percentile
- 54%
- 90th percentile
- 29.2%
- Min
This benchmark has a weight of 1.83 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 64% |
| 2 | GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54% |
| 3 | o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50% |
| 4 | GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.1% |
| 5 | GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.1% |
| 6 | GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.6% |
| 7 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29.2% |
Data credits: Data by LLM Stats