Skip to content

Benchmark

NepNewsBench v2 draft entity F1 (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

0.696
Mean
0.69
Median
0.068
Std dev
0.643
10th percentile
0.797
90th percentile
0.535
Min
0.5350.813
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) data0.797
Claude Haiku 4.5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.535
Claude Opus 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.813
Claude Sonnet 4.6Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.69
Claude Sonnet 5Anthropic via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.745
Gemini 3 FlashGoogle AI Studio via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.693
Gemini 3.1 Pro PreviewGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.676
Gemini 3.8 FlashGoogle AI Studio via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.677
Gemma 4 31B ITVenice via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.643
GLM 5.3Z.AI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.728
GPT-5.6 LunaOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.689
GPT-5.6 SolOpenAI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.677
Grok 4.6xAI via openrouter, reasoning low· NepNewsBench v2 (draft candidate release) data0.736
Kimi K3Moonshot AI via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.758
Qwen 3.8 27BAlibaba via openrouter, reasoning off· NepNewsBench v2 (draft candidate release) data0.591
Qwen3.8 MaxAlibaba via openrouter, reasoning minimal· NepNewsBench v2 (draft candidate release) data0.689

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.