{"schema":"most-annoying-ai-static-leaderboard/v1","view":"annoying","claim_ceiling":"OpenRouter rank is the captured programming/top-weekly discovery order. Benchmark rank is separate and exists only for complete verified runs. Tied scores share the same rank. Not run is not a zero; incomplete runs are not ranked.","score_contract":"Rank is the live certified 50-trap Most Annoying view. Released archives are immutable 100-task evidence bundles and can differ by date. Incomplete and missing rows are not zero.","rows":[{"benchmark_rank":1,"benchmark_state":"certified","display_name":"DeepSeek V4 Flash 0731","canonical_model_id":"deepseek/deepseek-v4-flash-0731","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":1},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"MiMo-V2.5","canonical_model_id":"xiaomi/mimo-v2.5","verified_mistakes":1,"clean_results":0,"unresolved":49,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":2},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Hy3","canonical_model_id":"tencent/hy3","verified_mistakes":0,"clean_results":5,"unresolved":45,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":3},{"benchmark_rank":21,"benchmark_state":"certified","display_name":"DeepSeek V4 Flash 0423","canonical_model_id":"deepseek/deepseek-v4-flash","verified_mistakes":40,"clean_results":10,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":4},{"benchmark_rank":15,"benchmark_state":"certified","display_name":"GPT-5.6 Luna","canonical_model_id":"openai/gpt-5.6-luna","verified_mistakes":9,"clean_results":41,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":5},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"Gemini 3.7 Flash","canonical_model_id":"google/gemini-3.7-flash","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":6},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"GLM 5.2","canonical_model_id":"z-ai/glm-5.2","verified_mistakes":0,"clean_results":49,"unresolved":1,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":7},{"benchmark_rank":24,"benchmark_state":"certified","display_name":"DeepSeek V4 Pro 0423","canonical_model_id":"deepseek/deepseek-v4-pro","verified_mistakes":46,"clean_results":4,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":8},{"benchmark_rank":12,"benchmark_state":"certified","display_name":"GPT-5.6 Sol","canonical_model_id":"openai/gpt-5.6-sol","verified_mistakes":2,"clean_results":48,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":9},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"MiniMax M3","canonical_model_id":"minimax/minimax-m3","verified_mistakes":0,"clean_results":23,"unresolved":27,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":10},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"Claude Opus 5","canonical_model_id":"anthropic/claude-opus-5","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":11},{"benchmark_rank":26,"benchmark_state":"certified","display_name":"Laguna S 2.1 (free)","canonical_model_id":"poolside/laguna-s-2.1","verified_mistakes":47,"clean_results":3,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":12},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Kimi K3","canonical_model_id":"moonshotai/kimi-k3","verified_mistakes":0,"clean_results":37,"unresolved":13,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":13},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"Claude Sonnet 5","canonical_model_id":"anthropic/claude-sonnet-5","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":14},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"DeepSeek V4 Pro 0813","canonical_model_id":"deepseek/deepseek-v4-pro-0813","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":15},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"GLM 5.3","canonical_model_id":"z-ai/glm-5.3","verified_mistakes":0,"clean_results":42,"unresolved":8,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":16},{"benchmark_rank":17,"benchmark_state":"certified","display_name":"Gemini 3 Flash Preview","canonical_model_id":"google/gemini-3-flash-preview","verified_mistakes":16,"clean_results":34,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":17},{"benchmark_rank":24,"benchmark_state":"certified","display_name":"Gemini 2.5 Flash Lite","canonical_model_id":"google/gemini-2.5-flash-lite","verified_mistakes":46,"clean_results":4,"unresolved":0,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":18},{"benchmark_rank":20,"benchmark_state":"certified","display_name":"Claude Sonnet 4.6","canonical_model_id":"anthropic/claude-sonnet-4.6","verified_mistakes":31,"clean_results":19,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":19},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"GLM 5.3 Flash","canonical_model_id":"z-ai/glm-5.3-flash","verified_mistakes":0,"clean_results":47,"unresolved":3,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":20},{"benchmark_rank":12,"benchmark_state":"certified","display_name":"GPT-5.6 Terra","canonical_model_id":"openai/gpt-5.6-terra","verified_mistakes":2,"clean_results":48,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":21},{"benchmark_rank":22,"benchmark_state":"certified","display_name":"Solar Pro 4","canonical_model_id":"upstage/solar-pro4","verified_mistakes":41,"clean_results":9,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":22},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Gemini 3.6 Flash","canonical_model_id":"google/gemini-3.6-flash","verified_mistakes":10,"clean_results":22,"unresolved":18,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":23},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"MiMo-V2.5-Pro","canonical_model_id":"xiaomi/mimo-v2.5-pro","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":24},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"Grok 4.6","canonical_model_id":"x-ai/grok-4.6","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":25},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Step 3.7 Flash","canonical_model_id":"stepfun/step-3.7-flash","verified_mistakes":0,"clean_results":10,"unresolved":40,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":26},{"benchmark_rank":18,"benchmark_state":"certified","display_name":"Claude Opus 4.8","canonical_model_id":"anthropic/claude-opus-4.8","verified_mistakes":24,"clean_results":26,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":27},{"benchmark_rank":12,"benchmark_state":"certified","display_name":"GPT-5.6 Luna Pro","canonical_model_id":"openai/gpt-5.6-luna-pro","verified_mistakes":2,"clean_results":48,"unresolved":0,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":28},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Gemma 4 26B A4B","canonical_model_id":"google/gemma-4-26b-a4b-it","verified_mistakes":41,"clean_results":4,"unresolved":5,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":29},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Qwen3.8 Max","canonical_model_id":"qwen/qwen3.8-max","verified_mistakes":0,"clean_results":44,"unresolved":6,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":30},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"GPT-5.5","canonical_model_id":"openai/gpt-5.5","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":31},{"benchmark_rank":16,"benchmark_state":"certified","display_name":"Claude Opus 4.7","canonical_model_id":"anthropic/claude-opus-4.7","verified_mistakes":14,"clean_results":36,"unresolved":0,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":32},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Claude Fable 5","canonical_model_id":"anthropic/claude-fable-5","verified_mistakes":0,"clean_results":10,"unresolved":40,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":33},{"benchmark_rank":22,"benchmark_state":"certified","display_name":"Claude Haiku 4.5","canonical_model_id":"anthropic/claude-haiku-4.5","verified_mistakes":41,"clean_results":9,"unresolved":0,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":34},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Gemini 3.1 Pro Preview","canonical_model_id":"google/gemini-3.1-pro-preview","verified_mistakes":3,"clean_results":37,"unresolved":10,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":35},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Qwen3.8 27B","canonical_model_id":"qwen/qwen3.8-27b","verified_mistakes":0,"clean_results":25,"unresolved":25,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":36},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Qwen3.7 Flash","canonical_model_id":"qwen/qwen3.7-flash","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":37},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Kimi K2.6","canonical_model_id":"moonshotai/kimi-k2.6","verified_mistakes":0,"clean_results":1,"unresolved":49,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":38},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Muse Spark 1.2 Contributor","canonical_model_id":"meta/muse-spark-1.2-contributor","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":39},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"DeepSeek V4 Flash Vision Exp","canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":40},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"Grok 4.5","canonical_model_id":"x-ai/grok-4.5","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":41},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Qwen3.6 35B A3B","canonical_model_id":"qwen/qwen3.6-35b-a3b","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":42},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"MiniMax M2.5","canonical_model_id":"minimax/minimax-m2.5","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":43},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Kimi K2.7 Code","canonical_model_id":"moonshotai/kimi-k2.7-code","verified_mistakes":1,"clean_results":48,"unresolved":1,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":44},{"benchmark_rank":1,"benchmark_state":"certified","display_name":"GPT-5.3-Codex","canonical_model_id":"openai/gpt-5.3-codex","verified_mistakes":0,"clean_results":50,"unresolved":0,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":45},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"GLM 5V Turbo","canonical_model_id":"z-ai/glm-5v-turbo","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_8b91abfc202748e5bbcb23c255514cef","run_completed_at":"2026-09-01T22:50:04.330589+00:00","archive_status":"available","archive_available_after":"2026-09-08T22:50:04.330589+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_8b91abfc202748e5bbcb23c255514cef.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_8b91abfc202748e5bbcb23c255514cef-evidence.json","openrouter_rank":46},{"benchmark_rank":19,"benchmark_state":"certified","display_name":"Claude Fable 5.1","canonical_model_id":"anthropic/claude-fable-5.1","verified_mistakes":26,"clean_results":24,"unresolved":0,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":null},{"benchmark_rank":null,"benchmark_state":"not_run","display_name":"Anthropic: Claude Opus 4.5","canonical_model_id":"anthropic/claude-opus-4.5","verified_mistakes":null,"clean_results":null,"unresolved":null,"denominator":null,"run_id":null,"run_completed_at":null,"archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":null,"openrouter_rank":null},{"benchmark_rank":11,"benchmark_state":"certified","display_name":"Gemini 3.8 Flash","canonical_model_id":"google/gemini-3.8-flash","verified_mistakes":1,"clean_results":49,"unresolved":0,"denominator":50,"run_id":"bench_9e15d94d6868451d9c90658cb75d27f6","run_completed_at":"2026-09-07T17:19:44.592026+00:00","archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":"npx genxis-gavel verify-archive most-annoying-bench_9e15d94d6868451d9c90658cb75d27f6-evidence.json","openrouter_rank":null},{"benchmark_rank":null,"benchmark_state":"not_run","display_name":"IBM: Granite 4.0 Micro","canonical_model_id":"ibm-granite/granite-4.0-h-micro","verified_mistakes":null,"clean_results":null,"unresolved":null,"denominator":null,"run_id":null,"run_completed_at":null,"archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":null,"openrouter_rank":null},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Granite 4.2 8B","canonical_model_id":"ibm-granite/granite-4.2-8b","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":null},{"benchmark_rank":null,"benchmark_state":"score_withheld","display_name":"Mercury 2.5 Preview","canonical_model_id":"inception/mercury-2.5-preview","verified_mistakes":0,"clean_results":0,"unresolved":50,"denominator":50,"run_id":"bench_77956877501b446a8b7286a04d2404bd","run_completed_at":"2026-09-02T10:43:22.086711+00:00","archive_status":"available","archive_available_after":"2026-09-09T10:43:22.086711+00:00","archive_download_url":"/v1/benchmarks/evidence-archives/bench_77956877501b446a8b7286a04d2404bd.json","verify_command":"npx genxis-gavel verify-archive most-annoying-bench_77956877501b446a8b7286a04d2404bd-evidence.json","openrouter_rank":null},{"benchmark_rank":null,"benchmark_state":"not_run","display_name":"OpenAI: GPT-6 Astra","canonical_model_id":"openai/gpt-6-astra","verified_mistakes":null,"clean_results":null,"unresolved":null,"denominator":null,"run_id":null,"run_completed_at":null,"archive_status":"not_available","archive_available_after":null,"archive_download_url":null,"verify_command":null,"openrouter_rank":null}]}