https://modelbench.marginalgains.jp/2026-11-13 https://modelbench.marginalgains.jp/table/2026-11-13 https://modelbench.marginalgains.jp/rankings/2026-11-13 https://modelbench.marginalgains.jp/rankings/all/2026-11-13 https://modelbench.marginalgains.jp/roles/2026-11-13 https://modelbench.marginalgains.jp/sources/2026-11-13 https://modelbench.marginalgains.jp/about/ https://modelbench.marginalgains.jp/models/claude-fable-5-2/2026-11-12 https://modelbench.marginalgains.jp/models/claude-mythos-5-2/2026-11-12 https://modelbench.marginalgains.jp/models/claude-opus-5-5/2026-11-12 https://modelbench.marginalgains.jp/models/claude-sonnet-5-5/2026-11-12 https://modelbench.marginalgains.jp/models/claude-haiku-5-5/2026-11-12 https://modelbench.marginalgains.jp/models/claude-fable-5-1/2026-11-12 https://modelbench.marginalgains.jp/models/claude-mythos-5-1/2026-11-12 https://modelbench.marginalgains.jp/models/claude-fable-5/2026-11-13 https://modelbench.marginalgains.jp/models/claude-mythos-5/ https://modelbench.marginalgains.jp/models/claude-mythos-preview/ https://modelbench.marginalgains.jp/models/claude-opus-5/2026-11-13 https://modelbench.marginalgains.jp/models/claude-opus-4-8/2026-11-13 https://modelbench.marginalgains.jp/models/claude-opus-4-7/2026-11-13 https://modelbench.marginalgains.jp/models/claude-opus-4-6/2026-11-13 https://modelbench.marginalgains.jp/models/claude-opus-4-5/2026-11-13 https://modelbench.marginalgains.jp/models/claude-sonnet-5/2026-11-12 https://modelbench.marginalgains.jp/models/claude-sonnet-4-6/2026-11-12 https://modelbench.marginalgains.jp/models/claude-sonnet-4-5/2026-11-13 https://modelbench.marginalgains.jp/models/claude-haiku-4-5/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-6-astra/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-6-1-sol/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-6-1-terra/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-6-luna/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-6-sol/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-5-6-sol/2026-11-13 https://modelbench.marginalgains.jp/models/gpt-5-6-terra/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-5-6-luna/2026-11-12 https://modelbench.marginalgains.jp/models/gpt-5-5/2026-11-13 https://modelbench.marginalgains.jp/models/gpt-5-4/2026-11-13 https://modelbench.marginalgains.jp/models/gpt-5-2/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-4-carbon/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-4-argon/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-3-8-flash/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-3-6-flash/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-3-5-flash-lite/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-3-1-pro-preview/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-3-1-flash-lite/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-3-flash-preview/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-2-5-pro/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-2-5-flash/2026-11-12 https://modelbench.marginalgains.jp/models/gemini-2-5-flash-lite/ https://modelbench.marginalgains.jp/models/gemini-3-7-flash/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-3-5-flash/2026-11-13 https://modelbench.marginalgains.jp/models/gemini-3-pro-preview/2026-11-13 https://modelbench.marginalgains.jp/models/grok-4-7/2026-11-12 https://modelbench.marginalgains.jp/models/grok-4-6/2026-11-12 https://modelbench.marginalgains.jp/models/grok-4-5/2026-11-13 https://modelbench.marginalgains.jp/models/deepseek-v4-pro/2026-11-12 https://modelbench.marginalgains.jp/models/deepseek-v4-1-flash-1017/2026-11-13 https://modelbench.marginalgains.jp/models/deepseek-v4-1-flash/2026-11-13 https://modelbench.marginalgains.jp/models/glm-5-3/2026-11-13 https://modelbench.marginalgains.jp/models/glm-5-3-flash/2026-11-13 https://modelbench.marginalgains.jp/models/glm-5-2/2026-11-13 https://modelbench.marginalgains.jp/models/glm-5/2026-11-13 https://modelbench.marginalgains.jp/models/kimi-k3-1-pro/2026-11-13 https://modelbench.marginalgains.jp/models/kimi-k3/2026-11-13 https://modelbench.marginalgains.jp/models/mistral-large-4/2026-11-12 https://modelbench.marginalgains.jp/models/qwen3-8-max/2026-11-13 https://modelbench.marginalgains.jp/models/qwen3-8-27b/2026-11-13 https://modelbench.marginalgains.jp/models/qwen3-5-397b-a17b/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/terminal-bench-4-0/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/terminal-bench-3-0/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/terminal-bench-2-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/terminal-bench-science-0-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/frontiercode-1-1-main/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/frontiercode-2-0/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/frontierswe-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cursorbench-4-0/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/deepswe-1-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/swe-sweep/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/gdpval-aa-2-1/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/gdpval-aa-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/aa-briefcase-1-1-elo/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/aa-briefcase-elo-unversioned/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/aa-briefcase-1-1-rubric/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/automationbench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/hle-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/hle-no-tools/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/hle-verified/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/osworld-2-1-partial/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/osworld-2-1-offline-subset/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/osworld-2-1-offline-partial/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/osworld-2-0/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/agents-last-exam-1-1/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/agents-last-exam-pass-rate/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/agents-last-exam-unspecified/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/chartography-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/chartography-no-tools/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/wandr/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/wandr-relaxed/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/benchcad-2-1-with-tools/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/benchcad-with-tools/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/benchcad-no-tools/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cve-rediscovery/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cyscenariobench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/de-novo-binder-design-24h/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/robodojo-sim/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/remote-labor-index/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/healthbench-professional-length-adjusted/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/healthbench-hard-length-adjusted/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/healthbench-professional/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/aa-intelligence-index-5-0/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/vals-index-2-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/vending-bench-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/blueprint-bench-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/graphwalks-bfs-256k-1m/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/graphwalks-bfs-128k/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/riemannbench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cwe-bench-1/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/exploitgym/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/sec-bench-pro/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/vals-finance-agent-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/harvey-legal-agent/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/vibe-code-bench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/posttrainbench/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/labbench-2/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/lvbench/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/gdp-pdf/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/charxiv-reasoning/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/biomysterybench-solvable/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/biomysterybench-difficult/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/eebench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cybergym/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/exploitbench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/officeqa-pro-2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/frontier-finance/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/swe-atlas-qna/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/cybench/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/gpqa-diamond/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/frontiermath-tiers-1-3-v2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/frontiermath-tier-4-v2/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/otis-mock-aime-2024-2025/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/simpleqa-verified/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/chess-puzzles-epoch/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/mirrorcode/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/epoch-capabilities-index/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/lmarena-text-style-control/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/lmarena-text-coding/2026-11-12 https://modelbench.marginalgains.jp/benchmarks/swe-bench-pro/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/swe-marathon-1-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/swe-marathon-unversioned/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/programbench-almost-solved/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/nl2repo-bench/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mls-bench-lite/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/automationbench-1-0-6/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/automationbench-public-600/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/browsecomp/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mcp-atlas/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/osworld-verified/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/charxiv-reasoning-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mmmu-pro/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mmmu-pro-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mathvision/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mathvision-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/babyvision-with-tools/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/zerobench-main-with-tools-pass5/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/officeqa-pro/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mrcr-v2-8-needle-128k/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/mrcr-v2-8-needle-1m/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/posttrainbench-1-2/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/tau2-bench-airline-1-0-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/tau2-bench-banking-knowledge-1-0-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/tau2-bench-retail-1-0-1/2026-11-13 https://modelbench.marginalgains.jp/benchmarks/tau2-bench-telecom-1-0-1/2026-11-13