Benchmark · KnowledgeCompetitive

LLM-JP · Overall

Updated 2025-01-20
Models tested
12
Top score
59.3
DeepSeek R1 Distill Qwen 32B
Median
45.1
min 15.6
Top-5 spread
σ 3.5
Competitive

Best score over time · one chart, every benchmark

LLM-JP · OVERALL6 MODELS · FRONTIER RUNNING MAX0255075100SCORE ↑Aug 24Oct 24Nov 24Dec 24Jan 25RELEASE DATE →benchgecko.ai/benchmark/jp-overall · frontier
Frontier on LLM-JP · Overall rose from 53.0 to 59.3 in 5 months · +6.4 points · latest leader DeepSeek R1 Distill Qwen 32B from DeepSeek.
Pink dots = frontier records · 3 totalClick to open model page

Same category · related evaluations