Individual experiment result
MMLU-ProX (DE)
Gemini 2.5 Flash Google
Exact match reasoning off provider-internal
79.6%
Exact match
Run details
- Date
- 2026-05-26
- Test cases
- 11,759
- Median latency
- 2.69s
- Total cost
- $28.89
- Avg. prompt tokens
- 1,664.9
- Avg. answer tokens
- 786
- Avg. reasoning tokens
- —
- Quantization
- provider-internal
About this benchmark
German MMLU-ProX across 14 subjects; primary metric accuracy. Legacy rows have 11,759 items. Corrected v1.1 rows have 11,737 after a frozen, model-independent manifest excludes 20 duplicated-gold translation collisions, one independently reviewed ambiguous source item, and one independently confirmed notation-translation collapse; the row's item count identifies the definition.
Subject breakdown
| Subject | Score |
|---|---|
| biology | 88.8% |
| business | 83.5% |
| chemistry | 86.9% |
| computer science | 85.1% |
| economics | 86.4% |
| engineering | 71.6% |
| health | 72.5% |
| history | 70.9% |
| law | 54.0% |
| math | 90.5% |
| other | 73.5% |
| philosophy | 70.9% |
| physics | 85.5% |
| psychology | 82.6% |
Provenance
- Canonical model
- google/gemini-2.5-flash
- Run ID
2026-05-26T15-52-44__vertex_ai__gemini-2.5-flash