Benchmark
Internal API instruction following (hard) Benchmark
What is Internal API instruction following (hard)?
Internal API instruction following (hard) benchmark - specific documentation not found in official sources. Benchmark Radar tracks 7 reported scores for…
- Modality
- text
- Evaluates
- structured output, general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 7
Source provenance
Internal API instruction following (hard) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.491 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.451 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.316 | 2025-04-14 | evidence |
| GPT-4.5 | OpenAI | 0.54 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.292 | 2024-08-06 | evidence |
| GPT-5 | OpenAI | 0.64 | 2025-08-07 | evidence |
| o3-mini | OpenAI | 0.5 | 2025-01-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.