OptimismBench / app /src /content /assets /data /robustness.json
seonglae's picture
article: interactive research piece for OptimismBench
1df44e8
Raw
History Blame Contribute Delete
1.64 kB
{
"note": "Mean Skew across 6 native-prompt languages (x) vs inter-language sigma (y), per model. Paper fig_alignment_stability.",
"models": [
{ "name": "GLM-4.7-flash", "skew": 15.97, "sigma": 2.34, "provider": "Zhipu" },
{ "name": "Mistral Small", "skew": 15.42, "sigma": 3.41, "provider": "Mistral" },
{ "name": "DeepSeek-V3.2", "skew": 13.78, "sigma": 1.69, "provider": "DeepSeek" },
{ "name": "Qwen3-Next-80B", "skew": 12.92, "sigma": 3.16, "provider": "Alibaba" },
{ "name": "GPT-5.4-mini", "skew": 12.35, "sigma": 2.10, "provider": "OpenAI" },
{ "name": "Llama-3.3-70B", "skew": 12.00, "sigma": 2.63, "provider": "Meta" },
{ "name": "Qwen3-235B", "skew": 11.10, "sigma": 1.31, "provider": "Alibaba" },
{ "name": "Mistral Large", "skew": 10.82, "sigma": 1.22, "provider": "Mistral" },
{ "name": "GPT-5.4", "skew": 10.49, "sigma": 0.95, "provider": "OpenAI" },
{ "name": "Gemini Flash 3", "skew": 6.48, "sigma": 0.92, "provider": "Google" },
{ "name": "Haiku 4.5", "skew": 6.30, "sigma": 1.16, "provider": "Anthropic" },
{ "name": "GLM-4.5-Air", "skew": 6.12, "sigma": 2.62, "provider": "Zhipu" },
{ "name": "Nemotron-3-super","skew": 5.07, "sigma": 1.85, "provider": "NVIDIA" },
{ "name": "Gemma-4-31B-IT", "skew": 1.73, "sigma": 0.75, "provider": "Google" },
{ "name": "Qwen3-32B", "skew": -1.65, "sigma": 1.27, "provider": "Alibaba" },
{ "name": "Opus 4.6", "skew": -5.38, "sigma": 0.89, "provider": "Anthropic" },
{ "name": "Sonnet 4.6", "skew": -8.33, "sigma": 0.54, "provider": "Anthropic" }
]
}