Skip to content

Benchmark

NepNewsBench v2 draft entity precision (mixed English and Nepali source questions)

Multilingual benchmarks compare model performance across languages. Higher scores are better.

Models measured
16
Scores recorded
16
Sources
1
IQ weight
No weight published

Score distribution

0.955
Mean
0.965
Median
0.037
Std dev
0.928
10th percentile
0.991
90th percentile
0.843
Min
0.8431
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
Claude Fable 5.1Anthropic via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.843
Claude Haiku 4.5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.959
Claude Opus 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.966
Claude Sonnet 4.6Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.96
Claude Sonnet 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.965
Gemini 3 FlashGoogle AI Studio via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.913
Gemini 3.1 Pro PreviewGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.93
Gemini 3.8 FlashGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.928
Gemma 4 31B ITVenice via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.943
GLM 5.3Z.AI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data1
GPT-5.6 LunaOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.971
GPT-5.6 SolOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.95
Grok 4.6xAI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.99
Kimi K3Moonshot AI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.991
Qwen 3.8 27BAlibaba via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.988
Qwen3.8 MaxAlibaba via openrouter, reasoning minimal· NepNewsBench v2 (draft candidate release) data0.979

Data credits: Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here.