{"models":[{"id":"kimi-k3-1-pro","name":"Kimi K3.1 Pro","provider":"Moonshot AI","providerId":"moonshot-ai","logo":"/providers/moonshot-ai.svg","score":70,"source":"https://www.kimi.ai/blog/kimi-k3-1-pro","publisher":"Moonshot AI","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — full set","tools":true,"settings":"Max effort; temperature=1.0; top_p=0.95; full 2500-question set.","notes":"","position":1,"score_rank":1},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":63.9,"source":"https://api-docs.deepseek.com/updates/","publisher":"DeepSeek","sourceType":"provider_reported","reportedAt":"2026-09-10","subset":"HLE — source does not specify subset","tools":true,"settings":"","notes":"2026-09-10 release. Do not transfer this score to the different 1017 checkpoint.","position":1,"score_rank":2},{"id":"glm-5-3","name":"GLM-5.3","provider":"Z.ai","providerId":"zai","logo":"/providers/zai.svg","score":62.5,"source":"https://z.ai/blog/glm-5.3","publisher":"Z.ai","sourceType":"provider_reported","reportedAt":"2026-08-14","subset":"HLE — source does not specify subset","tools":true,"settings":"temperature=1.0; top_p=0.95; max generation 163840 tokens; max context 300000 tokens; context management; GPT-5.6 Luna medium judge.","notes":"This report does not explicitly identify full vs text-only subset; do not infer it from later GLM reports.","position":1,"score_rank":3},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":60,"source":"https://api-docs.deepseek.com/updates/","publisher":"DeepSeek","sourceType":"provider_reported","reportedAt":"2026-08-13","subset":"HLE — source does not specify subset","tools":true,"settings":"","notes":"GA checkpoint 2026-08-13; report does not explicitly identify subset.","position":1,"score_rank":4},{"id":"kimi-k3","name":"Kimi K3","provider":"Moonshot AI","providerId":"moonshot-ai","logo":"/providers/moonshot-ai.svg","score":59.8,"source":"https://z.ai/blog/glm-5.3","publisher":"Z.ai","sourceType":"other","reportedAt":"2026-08-14","subset":"HLE — source does not specify subset","tools":true,"settings":"temperature=1.0; top_p=0.95; max generation 163840 tokens; max context 300000 tokens; context management; GPT-5.6 Luna medium judge.","notes":"Competitor result published by Z.ai; not a self-report by this model's provider. Subset not explicitly identified.","position":1,"score_rank":5},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":58.8,"source":"https://www.kimi.ai/blog/kimi-k3-1-pro","publisher":"Moonshot AI","sourceType":"other","reportedAt":null,"subset":"Stable HLE — full set","tools":true,"settings":"Max effort; competitor result in Moonshot AI report.","notes":"Competitor result, not a DeepSeek self-report; separate from 63.9 for September checkpoint.","position":1,"score_rank":6},{"id":"glm-5-3-flash","name":"GLM-5.3-Flash","provider":"Z.ai","providerId":"zai","logo":"/providers/zai.svg","score":55.3,"source":"https://huggingface.co/zai-org/GLM-5.3-Flash","publisher":"Z.ai","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — full set","tools":true,"settings":"Primary bench_53.png; full set; temperature 1; top_p .95; 163840 generation; 300K context; GPT-5.6 Luna judge","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":7},{"id":"glm-5-2","name":"GLM-5.2","provider":"Z.ai","providerId":"zai","logo":"/providers/zai.svg","score":54.7,"source":"https://huggingface.co/zai-org/GLM-5.2","publisher":"Z.ai","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":true,"settings":"Text-only per model-card footnote; 163840 generation; 300K context; no context management; GPT-5.5 medium judge","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":8},{"id":"kimi-k2-6","name":"Kimi K2.6","provider":"Moonshot AI","providerId":"moonshot-ai","logo":"/providers/moonshot-ai.svg","score":54,"source":"https://forum.moonshot.ai/t/meet-kimi-k2-6-advancing-open-source-coding/369","publisher":"Moonshot AI","sourceType":"provider_reported","reportedAt":null,"subset":"HLE — source does not specify subset","tools":true,"settings":"Provider announcement; tools enabled; subset not explicitly named in announcement","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":9},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","provider":"Moonshot AI","providerId":"moonshot-ai","logo":"/providers/moonshot-ai.svg","score":51,"source":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","publisher":"Moonshot AI","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":true,"settings":"Heavy configuration: parallel test-time compute. Text-only; retained separately from single-agent 44.9.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":10},{"id":"kimi-k2-5","name":"Kimi K2.5","provider":"Moonshot AI","providerId":"moonshot-ai","logo":"/providers/moonshot-ai.svg","score":50.2,"source":"https://huggingface.co/moonshotai/Kimi-K2.5","publisher":"Moonshot AI","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — full set","tools":true,"settings":"Full text and image set; search, code and browsing; 96K completion; simple context management; Hugging Face blocked","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":11},{"id":"mimo-v2-6-pro","name":"MiMo-V2.6-Pro","provider":"Xiaomi","providerId":"xiaomi","logo":"/providers/xiaomi.svg","score":49.4,"source":"https://artificialanalysis.ai/models/mimo-v2-6-pro","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"MiMo-V2.6-Pro; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":12},{"id":"deepseek-v4-pro-0424","name":"DeepSeek V4 Pro 0424","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":48.2,"source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","publisher":"DeepSeek","sourceType":"provider_reported","reportedAt":null,"subset":"HLE — source does not specify subset","tools":true,"settings":"Original V4 Think Max; HLE with tools; source does not explicitly identify subset","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":13},{"id":"minimax-m3-1-flash","name":"MiniMax M3.1 Flash","provider":"MiniMax","providerId":"minimax","logo":"/providers/minimax.ico","score":48,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"MiniMax-M3.1-Flash; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":14},{"id":"step-5-preview","name":"Step 5 Preview","provider":"StepFun","providerId":"stepfun","logo":"/providers/stepfun.png","score":46.5,"source":"https://artificialanalysis.ai/models/step-5","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"Step 5 Preview; original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":15},{"id":"deepseek-v4-flash-0420","name":"DeepSeek V4 Flash 0420","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":45.1,"source":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","publisher":"DeepSeek","sourceType":"provider_reported","reportedAt":null,"subset":"HLE — source does not specify subset","tools":true,"settings":"Original V4 Think Max; HLE with tools; source does not explicitly identify subset","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":16},{"id":"muse-spark-open","name":"Muse Spark Open","provider":"Meta","providerId":"meta","logo":"/providers/meta.svg","score":43.9,"source":"https://artificialanalysis.ai/models/muse-spark-open","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"Muse Spark Open (xhigh); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":17},{"id":"deepseek-v3-2","name":"DeepSeek V3.2","provider":"DeepSeek","providerId":"deepseek","logo":"/providers/deepseek.svg","score":40.8,"source":"https://huggingface.co/moonshotai/Kimi-K2.5","publisher":"Moonshot AI","sourceType":"provider_reported","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":true,"settings":"Published comparison table; DeepSeek dagger denotes text-only. Other rows use full text and image set.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":18},{"id":"minimax-m3","name":"MiniMax M3","provider":"MiniMax","providerId":"minimax","logo":"/providers/minimax.ico","score":38.9712696941613,"source":"https://artificialanalysis.ai/models/minimax-m3","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"MiniMax-M3; original HLE text-only 2,158 questions; no tools; not HLE Diamond","notes":"Imported from reviewed published source; no local benchmark execution.","position":1,"score_rank":19},{"id":"qwen3-8-27b","name":"Qwen3.8 27B","provider":"Qwen","providerId":"qwen","logo":"/providers/qwen.jpg","score":33.9,"source":"https://artificialanalysis.ai/models/qwen3-8-27b","publisher":"Artificial Analysis","sourceType":"independent","reportedAt":null,"subset":"Stable HLE — text-only subset","tools":false,"settings":"Qwen3.8 27B (xhigh); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal.","notes":"Published accuracy; settings retained separately. Not HLE-Diamond.","position":1,"score_rank":20}],"lastUpdated":"2026-11-05T05:17:23.064Z"}