https://evals.stream/ https://evals.stream/confronto/ https://evals.stream/eval/agenda-it/ https://evals.stream/eval/agenda-muto-it/ https://evals.stream/eval/agentic-it/ https://evals.stream/eval/agentic-long-it/ https://evals.stream/eval/agentic-xhard-it/ https://evals.stream/eval/aime-it/ https://evals.stream/eval/aime26-it/ https://evals.stream/eval/allucinazioni-it/ https://evals.stream/eval/bandi-it/ https://evals.stream/eval/faq-it/ https://evals.stream/eval/gpqa-biologia-it/ https://evals.stream/eval/gpqa-chimica-it/ https://evals.stream/eval/gpqa-fisica-it/ https://evals.stream/eval/gpqa-it/ https://evals.stream/eval/ifeval-hard-it/ https://evals.stream/eval/ifeval-it/ https://evals.stream/eval/klingon-it/ https://evals.stream/eval/magazzino-it/ https://evals.stream/eval/magazzino-muto-it/ https://evals.stream/eval/math-it/ https://evals.stream/eval/patente-it/ https://evals.stream/eval/pendolare-it/ https://evals.stream/eval/pregiudizi-it/ https://evals.stream/eval/sindarin-it/ https://evals.stream/eval/sycophancy-it/ https://evals.stream/eval/tool-use-it/ https://evals.stream/eval/trap-it/ https://evals.stream/eval/turni-it/ https://evals.stream/hardware/ https://evals.stream/modelli/ https://evals.stream/modelli/deepseek-v4-flash/ https://evals.stream/modelli/deepseek-v4-pro/ https://evals.stream/modelli/fable-5/ https://evals.stream/modelli/gemma-12b-local/ https://evals.stream/modelli/gemma-4-26b-local/ https://evals.stream/modelli/glm-5.2/ https://evals.stream/modelli/gpt-3.5/ https://evals.stream/modelli/gpt-4o/ https://evals.stream/modelli/gpt-5.4-mini/ https://evals.stream/modelli/gpt-5.4-nano/ https://evals.stream/modelli/gpt-5.4/ https://evals.stream/modelli/gpt-5.5/ https://evals.stream/modelli/gpt-oss-120b/ https://evals.stream/modelli/gpt-oss-20b-local/ https://evals.stream/modelli/haiku-4.5/ https://evals.stream/modelli/kimi-k2.5/ https://evals.stream/modelli/ministral-14b-local/ https://evals.stream/modelli/nemotron-30b-q4-local/ https://evals.stream/modelli/nemotron-ultra-550b/ https://evals.stream/modelli/opus-4.8/ https://evals.stream/modelli/qwen3-235b/ https://evals.stream/modelli/qwen3-35b-local/ https://evals.stream/modelli/qwen3-35b-q4-local/ https://evals.stream/modelli/qwen3-35b-q5-local/ https://evals.stream/modelli/qwen3.5-9b-local/ https://evals.stream/modelli/qwen3.6-27b-local/ https://evals.stream/modelli/sonnet-4.6/ https://evals.stream/modelli/sonnet-5/ https://evals.stream/scoring/ https://evals.stream/scoring/agentic/ https://evals.stream/scoring/ifeval/ https://evals.stream/scoring/mcq/ https://evals.stream/scoring/numeric/ https://evals.stream/scoring/tool-call/ https://evals.stream/use-case/