Tydiqa Benchmark

Explore score history ↗

Tydiqa is an AI benchmark in the Benchmark Radar catalog.

Released: 2020-03-11
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Tydiqa results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
BLOOMA	—	75.2	—	evidence
gpt-4-32k	—	71.5	—	evidence
Phi-3.5-mini-instruct	—	62.2	—	evidence
Phi-3.5-MoE-instruct	—	67.1	—	evidence
TuLRv6 - XXL	—	84.6	—	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 Tydiqa?

Tydiqa