{"api_version":"v1","generated_at":"2026-10-07T17:52:57Z","data_retrieved_at":"2026-10-07","harnesses":["artificial-analysis"],"counts":{"models":85,"benchmarks":24,"measured":396,"estimated":207,"mappings":34,"confidence":{"high":58,"medium":82,"low":67}},"benchmarks":[{"key":"terminal-bench/2.1","name":"terminal-bench","version":"2.1","label":"Terminal-Bench 2.1","capability":"agentic-terminal","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/terminalbench-2-1","n_measured":19,"n_estimated":17,"url":"https://benchgap.net/api/v1/benchmarks/terminal-bench/2.1.json","page":"https://benchgap.net/b/terminal-bench/2.1"},{"key":"terminal-bench/4.0","name":"terminal-bench","version":"4.0","label":"Terminal-Bench 4.0","capability":"agentic-terminal","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","n_measured":30,"n_estimated":6,"url":"https://benchgap.net/api/v1/benchmarks/terminal-bench/4.0.json","page":"https://benchgap.net/b/terminal-bench/4.0"},{"key":"terminal-bench-hard/1.0","name":"terminal-bench-hard","version":"1.0","label":"Terminal-Bench Hard","capability":"agentic-terminal","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/terminalbench-hard","n_measured":7,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/terminal-bench-hard/1.0.json","page":"https://benchgap.net/b/terminal-bench-hard/1.0"},{"key":"terminal-bench-science/0.1","name":"terminal-bench-science","version":"0.1","label":"Terminal-Bench Science 0.1","capability":"agentic-terminal","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/terminal-bench-science","n_measured":23,"n_estimated":9,"url":"https://benchgap.net/api/v1/benchmarks/terminal-bench-science/0.1.json","page":"https://benchgap.net/b/terminal-bench-science/0.1"},{"key":"analyst-agent/1.0","name":"analyst-agent","version":"1.0","label":"AA-AnalystAgent","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","n_measured":16,"n_estimated":28,"url":"https://benchgap.net/api/v1/benchmarks/analyst-agent/1.0.json","page":"https://benchgap.net/b/analyst-agent/1.0"},{"key":"apex-agents/1.0","name":"apex-agents","version":"1.0","label":"APEX-Agents","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/apex-agents-aa","n_measured":8,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/apex-agents/1.0.json","page":"https://benchgap.net/b/apex-agents/1.0"},{"key":"automationbench/1.0","name":"automationbench","version":"1.0","label":"AutomationBench","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/automationbench-aa","n_measured":30,"n_estimated":11,"url":"https://benchgap.net/api/v1/benchmarks/automationbench/1.0.json","page":"https://benchgap.net/b/automationbench/1.0"},{"key":"enterprise-ops-gym/1.0","name":"enterprise-ops-gym","version":"1.0","label":"EnterpriseOps-Gym","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","n_measured":15,"n_estimated":29,"url":"https://benchgap.net/api/v1/benchmarks/enterprise-ops-gym/1.0.json","page":"https://benchgap.net/b/enterprise-ops-gym/1.0"},{"key":"harvey-lab/1.0","name":"harvey-lab","version":"1.0","label":"Harvey LAB","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","n_measured":13,"n_estimated":34,"url":"https://benchgap.net/api/v1/benchmarks/harvey-lab/1.0.json","page":"https://benchgap.net/b/harvey-lab/1.0"},{"key":"itbench/sre","name":"itbench","version":"sre","label":"ITBench SRE","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/itbench-aa","n_measured":18,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/itbench/sre.json","page":"https://benchgap.net/b/itbench/sre"},{"key":"tau-bank/3-banking","name":"tau-bank","version":"3-banking","label":"τ³-Bench Banking","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/tau3-banking","n_measured":19,"n_estimated":28,"url":"https://benchgap.net/api/v1/benchmarks/tau-bank/3-banking.json","page":"https://benchgap.net/b/tau-bank/3-banking"},{"key":"tau-bench/2-telecom","name":"tau-bench","version":"2-telecom","label":"τ²-Bench Telecom","capability":"agentic-tool","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/tau2-bench","n_measured":7,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/tau-bench/2-telecom.json","page":"https://benchgap.net/b/tau-bench/2-telecom"},{"key":"livecodebench/1.0","name":"livecodebench","version":"1.0","label":"LiveCodeBench","capability":"coding","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/livecodebench","n_measured":5,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/livecodebench/1.0.json","page":"https://benchgap.net/b/livecodebench/1.0"},{"key":"scicode/1.0","name":"scicode","version":"1.0","label":"SciCode","capability":"coding","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/scicode","n_measured":30,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/scicode/1.0.json","page":"https://benchgap.net/b/scicode/1.0"},{"key":"aime-2025/2025","name":"aime-2025","version":"2025","label":"AIME 2025","capability":"math","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/aime-2025","n_measured":5,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/aime-2025/2025.json","page":"https://benchgap.net/b/aime-2025/2025"},{"key":"math-500/1.0","name":"math-500","version":"1.0","label":"MATH-500","capability":"math","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/math-500","n_measured":5,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/math-500/1.0.json","page":"https://benchgap.net/b/math-500/1.0"},{"key":"critpt/1.0","name":"critpt","version":"1.0","label":"CritPt","capability":"knowledge","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/critpt","n_measured":30,"n_estimated":6,"url":"https://benchgap.net/api/v1/benchmarks/critpt/1.0.json","page":"https://benchgap.net/b/critpt/1.0"},{"key":"global-mmlu-lite/1.0","name":"global-mmlu-lite","version":"1.0","label":"Global-MMLU-Lite","capability":"knowledge","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","n_measured":5,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/global-mmlu-lite/1.0.json","page":"https://benchgap.net/b/global-mmlu-lite/1.0"},{"key":"gpqa/diamond","name":"gpqa","version":"diamond","label":"GPQA Diamond","capability":"knowledge","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/gpqa-diamond","n_measured":19,"n_estimated":17,"url":"https://benchgap.net/api/v1/benchmarks/gpqa/diamond.json","page":"https://benchgap.net/b/gpqa/diamond"},{"key":"hle/1.0","name":"hle","version":"1.0","label":"Humanity's Last Exam","capability":"knowledge","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","n_measured":30,"n_estimated":6,"url":"https://benchgap.net/api/v1/benchmarks/hle/1.0.json","page":"https://benchgap.net/b/hle/1.0"},{"key":"mmlu-pro/1.0","name":"mmlu-pro","version":"1.0","label":"MMLU-Pro","capability":"knowledge","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/mmlu-pro","n_measured":5,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/mmlu-pro/1.0.json","page":"https://benchgap.net/b/mmlu-pro/1.0"},{"key":"ifbench/1.0","name":"ifbench","version":"1.0","label":"IFBench","capability":"instruction-following","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/ifbench","n_measured":7,"n_estimated":0,"url":"https://benchgap.net/api/v1/benchmarks/ifbench/1.0.json","page":"https://benchgap.net/b/ifbench/1.0"},{"key":"gdp-pdf/1.0","name":"gdp-pdf","version":"1.0","label":"GDP.pdf","capability":"vision","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/gdp-pdf","n_measured":30,"n_estimated":3,"url":"https://benchgap.net/api/v1/benchmarks/gdp-pdf/1.0.json","page":"https://benchgap.net/b/gdp-pdf/1.0"},{"key":"mmmu-pro/1.0","name":"mmmu-pro","version":"1.0","label":"MMMU-Pro","capability":"vision","harness":"artificial-analysis","source_url":"https://artificialanalysis.ai/evaluations/mmmu-pro","n_measured":20,"n_estimated":13,"url":"https://benchgap.net/api/v1/benchmarks/mmmu-pro/1.0.json","page":"https://benchgap.net/b/mmmu-pro/1.0"}]}