IFEval

Explore score history ↗

IFEval is an AI benchmark in the Benchmark Radar catalog.

Released: 2023-11-15
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

IFEval results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude 3.7 Sonnet	—	93.2	—	evidence
Gemma 3 27B	—	90.4	—	evidence
Llama 3.3 70B Instruct	—	92.1	—	evidence
Nova Pro	—	92.1	—	evidence
o3-mini	—	93.9	—	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.

Which sources cite IFEval?

IFEval