C-Eval

Explore score history ↗

C-Eval is an AI benchmark in the Benchmark Radar catalog.

Released: 2023-05-15
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

C-Eval results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude-3-Opus	—	71.7	—	evidence
Deepseek v3	—	90.1	—	evidence
GLM 4.5	—	86.9	—	evidence
Kimi K2	—	92.5	—	evidence
Qwen3-225B-A22B	—	89.6	—	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 C-Eval?

C-Eval