Skip to content

Benchmark

NepNewsBench v2 draft core fact recall (all 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

0.906
Mean
0.906
Median
0.03
Std dev
0.874
10th percentile
0.955
90th percentile
0.838
Min
0.8380.956
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) data0.956
Claude Haiku 4.5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.88
Claude Opus 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.955
Claude Sonnet 4.6Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.93
Claude Sonnet 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.923
Gemini 3 FlashGoogle AI Studio via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.9
Gemini 3.1 Pro PreviewGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.874
Gemini 3.8 FlashGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.899
Gemma 4 31B ITVenice via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.868
GLM 5.3Z.AI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.93
GPT-5.6 LunaOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.897
GPT-5.6 SolOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.902
Grok 4.6xAI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.91
Kimi K3Moonshot AI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.931
Qwen 3.8 27BAlibaba via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.838
Qwen3.8 MaxAlibaba via openrouter, reasoning minimal· NepNewsBench v2 (draft candidate release) data0.906

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.