{"$k":["studySlug","chartId","series","point","metric","label","value","unit","display","n","ci","spanKind","context","calculation","range","polarity"],"$r":[["swe-bench-opus-vs-sonnet","swebench-opus-sonnet-resolved","Resolved","Claude Opus 5.5 (Agent, new build)","swebench-opus-sonnet-resolved","Resolved on the same 3 SWE-bench Verified instances (interim)",0.6667,"rate","67% (2/3)",3,[0.2077,0.9385],"ci95","Agent · new build · SWE-bench Verified, interim paired probe","\u0001","\u0001","\u0001"],["swe-bench-opus-vs-sonnet","swebench-opus-sonnet-cost-per-attempt","List-price cost per attempt","Claude Opus 5.5 (Agent, new build)","swebench-opus-sonnet-cost-per-attempt","List-price cost per attempt (calculation)",7.59,"usd","$7.59",3,"\u0001","\u0001","Agent · new build · SWE-bench Verified, interim paired probe",true,"\u0001","\u0001"],["swe-bench-opus-vs-sonnet","swebench-opus-sonnet-minutes","Worker minutes per attempt","Claude Opus 5.5 (Agent, new build)","swebench-opus-sonnet-minutes","Worker time per attempt",20.26,"minutes","20.3 min",3,"\u0001","minmax","Agent · new build · SWE-bench Verified, interim paired probe","\u0001",[9.76,25.29],"\u0001"],["model-head-to-head","h2h-pass-rate","Pass rate","Claude Opus 5.5 (high) · Claude Code","h2h-pass-rate","Pass rate on five validated tasks",1,"rate","100% (15/15)",15,[0.7961,1],"ci95","Claude Code · effort high · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-pass-rate","Pass rate","Claude Opus 5.5 · Claude Code","h2h-pass-rate","Pass rate on five validated tasks",1,"rate","100% (15/15)",15,[0.7961,1],"ci95","Claude Code · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-pass-rate","Pass rate","Claude Opus 5.5 (low) · Claude Code","h2h-pass-rate","Pass rate on five validated tasks",1,"rate","100% (15/15)",15,[0.7961,1],"ci95","Claude Code · effort low · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-total-latency","Total time per call","Claude Opus 5.5 (high) · Claude Code","h2h-total-latency","Total time per call",2.71,"seconds","2.71 s",15,"\u0001","minmax","Claude Code · effort high · five short validated tasks","\u0001",[2.45,11.78],"\u0001"],["model-head-to-head","h2h-total-latency","Total time per call","Claude Opus 5.5 · Claude Code","h2h-total-latency","Total time per call",2.75,"seconds","2.75 s",15,"\u0001","minmax","Claude Code · five short validated tasks","\u0001",[2.47,8.91],"\u0001"],["model-head-to-head","h2h-total-latency","Total time per call","Claude Opus 5.5 (low) · Claude Code","h2h-total-latency","Total time per call",2.83,"seconds","2.83 s",15,"\u0001","minmax","Claude Code · effort low · five short validated tasks","\u0001",[2.35,6.62],"\u0001"],["model-head-to-head","h2h-first-useful-latency","Time to first useful output","Claude Opus 5.5 (high) · Claude Code","h2h-first-useful-latency","Time to first useful output",2.04,"seconds","2.04 s",15,"\u0001","minmax","Claude Code · effort high · five short validated tasks","\u0001",[1.4,9.94],"\u0001"],["model-head-to-head","h2h-first-useful-latency","Time to first useful output","Claude Opus 5.5 · Claude Code","h2h-first-useful-latency","Time to first useful output",1.92,"seconds","1.92 s",15,"\u0001","minmax","Claude Code · five short validated tasks","\u0001",[1.56,7.23],"\u0001"],["model-head-to-head","h2h-first-useful-latency","Time to first useful output","Claude Opus 5.5 (low) · Claude Code","h2h-first-useful-latency","Time to first useful output",2.39,"seconds","2.39 s",15,"\u0001","minmax","Claude Code · effort low · five short validated tasks","\u0001",[1.45,4.9],"\u0001"],["model-head-to-head","h2h-input-tokens","Cache read","Claude Opus 5.5 (high) · Claude Code","h2h-input-tokens/Cache read","Input tokens per call: what the CLI sends (Cache read)",1463,"tokens","1,463",15,"\u0001","\u0001","Claude Code · effort high · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-input-tokens","Cache read","Claude Opus 5.5 · Claude Code","h2h-input-tokens/Cache read","Input tokens per call: what the CLI sends (Cache read)",1401,"tokens","1,401",15,"\u0001","\u0001","Claude Code · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-input-tokens","Cache read","Claude Opus 5.5 (low) · Claude Code","h2h-input-tokens/Cache read","Input tokens per call: what the CLI sends (Cache read)",1463,"tokens","1,463",15,"\u0001","\u0001","Claude Code · effort low · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-input-tokens","Other input","Claude Opus 5.5 (high) · Claude Code","h2h-input-tokens/Other input","Input tokens per call: what the CLI sends (Other input)",619,"tokens","619",15,"\u0001","\u0001","Claude Code · effort high · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-input-tokens","Other input","Claude Opus 5.5 · Claude Code","h2h-input-tokens/Other input","Input tokens per call: what the CLI sends (Other input)",680,"tokens","680",15,"\u0001","\u0001","Claude Code · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-input-tokens","Other input","Claude Opus 5.5 (low) · Claude Code","h2h-input-tokens/Other input","Input tokens per call: what the CLI sends (Other input)",618,"tokens","618",15,"\u0001","\u0001","Claude Code · effort low · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-output-tokens","Output tokens","Claude Opus 5.5 (high) · Claude Code","h2h-output-tokens/Output tokens","Output tokens per call (Output tokens)",78,"tokens","78",15,"\u0001","\u0001","Claude Code · effort high · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-output-tokens","Output tokens","Claude Opus 5.5 · Claude Code","h2h-output-tokens/Output tokens","Output tokens per call (Output tokens)",64,"tokens","64",15,"\u0001","\u0001","Claude Code · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-output-tokens","Output tokens","Claude Opus 5.5 (low) · Claude Code","h2h-output-tokens/Output tokens","Output tokens per call (Output tokens)",64,"tokens","64",15,"\u0001","\u0001","Claude Code · effort low · five short validated tasks","\u0001","\u0001","\u0001"],["model-head-to-head","h2h-list-price-per-call","Cost per call","Claude Opus 5.5 (high) · Claude Code","h2h-list-price-per-call","List-price cost per call (calculation)",0.00694,"usd","$0.0069",15,"\u0001","minmax","Claude Code · effort high · five short validated tasks",true,[0.00592,0.02708],"\u0001"],["model-head-to-head","h2h-list-price-per-call","Cost per call","Claude Opus 5.5 · Claude Code","h2h-list-price-per-call","List-price cost per call (calculation)",0.00688,"usd","$0.0069",15,"\u0001","minmax","Claude Code · five short validated tasks",true,[0.00592,0.02226],"\u0001"],["model-head-to-head","h2h-list-price-per-call","Cost per call","Claude Opus 5.5 (low) · Claude Code","h2h-list-price-per-call","List-price cost per call (calculation)",0.00688,"usd","$0.0069",15,"\u0001","minmax","Claude Code · effort low · five short validated tasks",true,[0.00582,0.01793],"\u0001"],["model-head-to-head","h2h-cost-per-pass","Cost per pass","Claude Opus 5.5 (low) · Claude Code","h2h-cost-per-pass","List-price cost per passing answer (calculation)",0.00829,"usd","$0.0083",15,"\u0001","\u0001","Claude Code · effort low · five short validated tasks",true,"\u0001","\u0001"],["model-head-to-head","h2h-cost-per-pass","Cost per pass","Claude Opus 5.5 · Claude Code","h2h-cost-per-pass","List-price cost per passing answer (calculation)",0.01009,"usd","$0.010",15,"\u0001","\u0001","Claude Code · five short validated tasks",true,"\u0001","\u0001"],["model-head-to-head","h2h-cost-per-pass","Cost per pass","Claude Opus 5.5 (high) · Claude Code","h2h-cost-per-pass","List-price cost per passing answer (calculation)",0.01049,"usd","$0.010",15,"\u0001","\u0001","Claude Code · effort high · five short validated tasks",true,"\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-pass-rate","Strict pass","Claude Opus 5.5 · Claude Code","hard-h2h-pass-rate/Strict pass","Pass rate on eight hard tasks (Strict pass)",1,"rate","100% (24/24)",24,[0.862,1],"ci95","Claude Code · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-pass-rate","Strict pass","Claude Opus 5.5 (high) · Claude Code","hard-h2h-pass-rate/Strict pass","Pass rate on eight hard tasks (Strict pass)",1,"rate","100% (24/24)",24,[0.862,1],"ci95","Claude Code · effort high · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-pass-rate","Lenient (format misses counted)","Claude Opus 5.5 · Claude Code","hard-h2h-pass-rate/Lenient (format misses counted)","Pass rate on eight hard tasks (Lenient (format misses counted))",1,"rate","100% (24/24)",24,[0.862,1],"ci95","Claude Code · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-pass-rate","Lenient (format misses counted)","Claude Opus 5.5 (high) · Claude Code","hard-h2h-pass-rate/Lenient (format misses counted)","Pass rate on eight hard tasks (Lenient (format misses counted))",1,"rate","100% (24/24)",24,[0.862,1],"ci95","Claude Code · effort high · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-total-latency","Total time per call on hard tasks (separate batches)","Claude Opus 5.5 · Claude Code","hard-h2h-total-latency","Total time per call on hard tasks (separate batches)",9.18,"seconds","9.18 s",24,"\u0001","minmax","Claude Code · eight hard validated tasks","\u0001",[4.24,27.21],"\u0001"],["hard-model-head-to-head","hard-h2h-total-latency","Total time per call on hard tasks (separate batches)","Claude Opus 5.5 (high) · Claude Code","hard-h2h-total-latency","Total time per call on hard tasks (separate batches)",11.03,"seconds","11.0 s",24,"\u0001","minmax","Claude Code · effort high · eight hard validated tasks","\u0001",[3.63,63],"\u0001"],["hard-model-head-to-head","hard-h2h-first-useful-latency","Time to first useful output on hard tasks","Claude Opus 5.5 · Claude Code","hard-h2h-first-useful-latency","Time to first useful output on hard tasks",6.78,"seconds","6.78 s",24,"\u0001","minmax","Claude Code · eight hard validated tasks","\u0001",[2.39,21.77],"\u0001"],["hard-model-head-to-head","hard-h2h-first-useful-latency","Time to first useful output on hard tasks","Claude Opus 5.5 (high) · Claude Code","hard-h2h-first-useful-latency","Time to first useful output on hard tasks",7.13,"seconds","7.13 s",24,"\u0001","minmax","Claude Code · effort high · eight hard validated tasks","\u0001",[2.15,56.23],"\u0001"],["hard-model-head-to-head","hard-h2h-output-tokens","Output tokens","Claude Opus 5.5 · Claude Code","hard-h2h-output-tokens/Output tokens","Output tokens per call on hard tasks (Output tokens)",945,"tokens","945",24,"\u0001","\u0001","Claude Code · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-output-tokens","Output tokens","Claude Opus 5.5 (high) · Claude Code","hard-h2h-output-tokens/Output tokens","Output tokens per call on hard tasks (Output tokens)",1052,"tokens","1,052",24,"\u0001","\u0001","Claude Code · effort high · eight hard validated tasks","\u0001","\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-cost-per-pass","Cost per strict pass","Claude Opus 5.5 · Claude Code","hard-h2h-cost-per-pass","List-price cost per strict pass on hard tasks (calculation)",0.02824,"usd","$0.028",24,"\u0001","\u0001","Claude Code · eight hard validated tasks",true,"\u0001","\u0001"],["hard-model-head-to-head","hard-h2h-cost-per-pass","Cost per strict pass","Claude Opus 5.5 (high) · Claude Code","hard-h2h-cost-per-pass","List-price cost per strict pass on hard tasks (calculation)",0.03337,"usd","$0.033",24,"\u0001","\u0001","Claude Code · effort high · eight hard validated tasks",true,"\u0001","\u0001"],["coding-agents-head-to-head","coding-agents-pass-rate","Passed every hidden check","Claude Opus 5.5 · Claude Code","coding-agents-pass-rate","Coding sessions that passed every hidden check",1,"rate","100% (12/12)",12,[0.7575,1],"ci95","Claude Code · six small repository tasks with hidden tests","\u0001","\u0001","\u0001"],["coding-agents-head-to-head","coding-agents-wall-time","Wall time per session","Claude Opus 5.5 · Claude Code","coding-agents-wall-time","Time per coding session",56.9,"seconds","56.9 s",12,"\u0001","minmax","Claude Code · six small repository tasks with hidden tests","\u0001",[29.8,185.8],"\u0001"],["coding-agents-head-to-head","coding-agents-tool-calls","Tool calls per session","Claude Opus 5.5 · Claude Code","coding-agents-tool-calls","Tool calls per coding session",7.5,"calls","7.5",12,"\u0001","minmax","Claude Code · six small repository tasks with hidden tests","\u0001",[5,14],"\u0001"],["coding-agents-head-to-head","coding-agents-cost-per-pass","List-price cost per pass","Claude Opus 5.5 · Claude Code","coding-agents-cost-per-pass","List-price cost per passing coding session (calculation)",0.2229,"usd","$0.22",12,"\u0001","\u0001","Claude Code · six small repository tasks with hidden tests",true,"\u0001","\u0001"],["effort-ladder","effort-ladder-pass-rate","Strict pass","Claude Opus 5.5 (low) · Claude Code","effort-ladder-pass-rate","Strict pass rate by effort on eight hard tasks",1,"rate","100% (16/16)",16,[0.8064,1],"ci95","Claude Code · effort low · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-pass-rate","Strict pass","Claude Opus 5.5 (medium) · Claude Code","effort-ladder-pass-rate","Strict pass rate by effort on eight hard tasks",1,"rate","100% (16/16)",16,[0.8064,1],"ci95","Claude Code · effort medium · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-pass-rate","Strict pass","Claude Opus 5.5 (high) · Claude Code","effort-ladder-pass-rate","Strict pass rate by effort on eight hard tasks",1,"rate","100% (16/16)",16,[0.8064,1],"ci95","Claude Code · effort high · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-pass-rate","Strict pass","Claude Opus 5.5 · Claude Code","effort-ladder-pass-rate","Strict pass rate by effort on eight hard tasks",1,"rate","100% (16/16)",16,[0.8064,1],"ci95","Claude Code · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-total-latency","Total time per call by effort on hard tasks","Claude Opus 5.5 (low) · Claude Code","effort-ladder-total-latency","Total time per call by effort on hard tasks",7.5,"seconds","7.50 s",16,"\u0001","minmax","Claude Code · effort low · eight hard validated tasks, effort ladder","\u0001",[3.34,15.82],"\u0001"],["effort-ladder","effort-ladder-total-latency","Total time per call by effort on hard tasks","Claude Opus 5.5 (medium) · Claude Code","effort-ladder-total-latency","Total time per call by effort on hard tasks",9.72,"seconds","9.72 s",16,"\u0001","minmax","Claude Code · effort medium · eight hard validated tasks, effort ladder","\u0001",[4.78,31.36],"\u0001"],["effort-ladder","effort-ladder-total-latency","Total time per call by effort on hard tasks","Claude Opus 5.5 (high) · Claude Code","effort-ladder-total-latency","Total time per call by effort on hard tasks",10.11,"seconds","10.1 s",16,"\u0001","minmax","Claude Code · effort high · eight hard validated tasks, effort ladder","\u0001",[3.63,63],"\u0001"],["effort-ladder","effort-ladder-total-latency","Total time per call by effort on hard tasks","Claude Opus 5.5 · Claude Code","effort-ladder-total-latency","Total time per call by effort on hard tasks",9.18,"seconds","9.18 s",16,"\u0001","minmax","Claude Code · eight hard validated tasks, effort ladder","\u0001",[4.24,27.21],"\u0001"],["effort-ladder","effort-ladder-output-tokens","Output tokens","Claude Opus 5.5 (low) · Claude Code","effort-ladder-output-tokens/Output tokens","Output tokens per call by effort on hard tasks (Output tokens)",594,"tokens","594",16,"\u0001","\u0001","Claude Code · effort low · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-output-tokens","Output tokens","Claude Opus 5.5 (medium) · Claude Code","effort-ladder-output-tokens/Output tokens","Output tokens per call by effort on hard tasks (Output tokens)",853,"tokens","853",16,"\u0001","\u0001","Claude Code · effort medium · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-output-tokens","Output tokens","Claude Opus 5.5 (high) · Claude Code","effort-ladder-output-tokens/Output tokens","Output tokens per call by effort on hard tasks (Output tokens)",1052,"tokens","1,052",16,"\u0001","\u0001","Claude Code · effort high · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-output-tokens","Output tokens","Claude Opus 5.5 · Claude Code","effort-ladder-output-tokens/Output tokens","Output tokens per call by effort on hard tasks (Output tokens)",945,"tokens","945",16,"\u0001","\u0001","Claude Code · eight hard validated tasks, effort ladder","\u0001","\u0001","\u0001"],["effort-ladder","effort-ladder-cost-per-pass","Cost per strict pass","Claude Opus 5.5 (low) · Claude Code","effort-ladder-cost-per-pass","List-price cost per strict pass by effort (calculation)",0.02115,"usd","$0.021",16,"\u0001","\u0001","Claude Code · effort low · eight hard validated tasks, effort ladder",true,"\u0001","\u0001"],["effort-ladder","effort-ladder-cost-per-pass","Cost per strict pass","Claude Opus 5.5 (medium) · Claude Code","effort-ladder-cost-per-pass","List-price cost per strict pass by effort (calculation)",0.02947,"usd","$0.029",16,"\u0001","\u0001","Claude Code · effort medium · eight hard validated tasks, effort ladder",true,"\u0001","\u0001"],["effort-ladder","effort-ladder-cost-per-pass","Cost per strict pass","Claude Opus 5.5 (high) · Claude Code","effort-ladder-cost-per-pass","List-price cost per strict pass by effort (calculation)",0.03368,"usd","$0.034",16,"\u0001","\u0001","Claude Code · effort high · eight hard validated tasks, effort ladder",true,"\u0001","\u0001"],["effort-ladder","effort-ladder-cost-per-pass","Cost per strict pass","Claude Opus 5.5 · Claude Code","effort-ladder-cost-per-pass","List-price cost per strict pass by effort (calculation)",0.02893,"usd","$0.029",16,"\u0001","\u0001","Claude Code · eight hard validated tasks, effort ladder",true,"\u0001","\u0001"],["caching-consistency","caching-cost-with-without","With the cache, as recorded","Claude Opus 5.5 · Claude Code","caching-cost-with-without/With the cache, as recorded","List-price cost of 5-question sessions with and without the cache (calculation) (With the cache, as recorded)",0.255057,"usd","$0.26",15,"\u0001","\u0001","Claude Code · calculation: 5-turn cached sessions over a fixed ledger",true,"\u0001","\u0001"],["caching-consistency","caching-cost-with-without","Without a cache: every input token at the input price","Claude Opus 5.5 · Claude Code","caching-cost-with-without/Without a cache: every input token at the input price","List-price cost of 5-question sessions with and without the cache (calculation) (Without a cache: every input token at the input price)",0.544228,"usd","$0.54",15,"\u0001","\u0001","Claude Code · calculation: 5-turn cached sessions over a fixed ledger",true,"\u0001","\u0001"],["caching-consistency","caching-latency-first-vs-later","Turn 1 (writes the ledger to the cache)","Claude Opus 5.5 · Claude Code","caching-latency-first-vs-later/Turn 1 (writes the ledger to the cache)","Time per turn: first turn vs later turns in a cached session (Turn 1 (writes the ledger to the cache))",1.9,"seconds","1.90 s",3,"\u0001","minmax","Claude Code · 5-turn cached sessions over a fixed ledger","\u0001",[1.78,4.36],"\u0001"],["caching-consistency","caching-latency-first-vs-later","Turns 2-5 (read the ledger from the cache)","Claude Opus 5.5 · Claude Code","caching-latency-first-vs-later/Turns 2-5 (read the ledger from the cache)","Time per turn: first turn vs later turns in a cached session (Turns 2-5 (read the ledger from the cache))",2.4,"seconds","2.40 s",12,"\u0001","minmax","Claude Code · 5-turn cached sessions over a fixed ledger","\u0001",[1.63,12.67],"\u0001"],["cost-thought-experiments","repriced-cost-per-resolved","Repriced cost per resolved instance","Claude Opus 5.5","repriced-cost-per-resolved","Thought experiment: the same tokens at other list prices",5.753,"usd","$5.75","\u0001","\u0001","\u0001","calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["cost-thought-experiments","prompt-cache-savings","With caching (as recorded)","Claude Opus 5.5","prompt-cache-savings/With caching (as recorded)","Thought experiment: what prompt caching saved (With caching (as recorded))",143.83,"usd","$143.83","\u0001","\u0001","\u0001","calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["cost-thought-experiments","prompt-cache-savings","Without caching","Claude Opus 5.5","prompt-cache-savings/Without caching","Thought experiment: what prompt caching saved (Without caching)",686.66,"usd","$686.66","\u0001","\u0001","\u0001","calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","1-hour write (2× input), whole prefix new","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-reads/1-hour write (2× input), whole prefix new","Reuses before a cached prefix costs less, by model and write type (calculation) (1-hour write (2× input), whole prefix new)",1.05,"score","1.05","\u0001","\u0001","\u0001","cache read $0.2 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","1-hour write (2× input), whole prefix new","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-reads/1-hour write (2× input), whole prefix new","Reuses before a cached prefix costs less, by model and write type (calculation) (1-hour write (2× input), whole prefix new)",1.11,"score","1.11","\u0001","\u0001","\u0001","cache read $0.4 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","1-hour write, pooled n = 6 session share, 19% already cached (as recorded)","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-reads/1-hour write, pooled n = 6 session share, 19% already cached (as recorded)","Reuses before a cached prefix costs less, by model and write type (calculation) (1-hour write, pooled n = 6 session share, 19% already cached (as recorded))",0.67,"score","0.67","\u0001","\u0001","\u0001","cache read $0.2 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","1-hour write, pooled n = 6 session share, 19% already cached (as recorded)","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-reads/1-hour write, pooled n = 6 session share, 19% already cached (as recorded)","Reuses before a cached prefix costs less, by model and write type (calculation) (1-hour write, pooled n = 6 session share, 19% already cached (as recorded))",0.72,"score","0.72","\u0001","\u0001","\u0001","cache read $0.4 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","5-minute write (1.25× input, an assumption)","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-reads/5-minute write (1.25× input, an assumption)","Reuses before a cached prefix costs less, by model and write type (calculation) (5-minute write (1.25× input, an assumption))",0.26,"score","0.26","\u0001","\u0001","\u0001","cache read $0.2 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-reads","5-minute write (1.25× input, an assumption)","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-reads/5-minute write (1.25× input, an assumption)","Reuses before a cached prefix costs less, by model and write type (calculation) (5-minute write (1.25× input, an assumption))",0.28,"score","0.28","\u0001","\u0001","\u0001","cache read $0.4 per M · calculation: Agent’s recorded tokens at this model’s list price",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","1 turn","cache-break-even-cost-curve/1 turn","Cost of a reused prefix with and without the cache, by session length (calculation): 1 turn",31.31,"usd","$31.31","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","2 turns","cache-break-even-cost-curve/2 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 2 turns",62.62,"usd","$62.62","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","3 turns","cache-break-even-cost-curve/3 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 3 turns",93.94,"usd","$93.94","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","5 turns","cache-break-even-cost-curve/5 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 5 turns",156.56,"usd","$156.56","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","10 turns","cache-break-even-cost-curve/10 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 10 turns",313.12,"usd","$313.12","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (no cache)","20 turns","cache-break-even-cost-curve/20 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 20 turns",626.24,"usd","$626.24","\u0001","\u0001","\u0001","no cache",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","1 turn","cache-break-even-cost-curve/1 turn","Cost of a reused prefix with and without the cache, by session length (calculation): 1 turn",62.62,"usd","$62.62","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","2 turns","cache-break-even-cost-curve/2 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 2 turns",64.19,"usd","$64.19","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","3 turns","cache-break-even-cost-curve/3 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 3 turns",65.76,"usd","$65.76","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","5 turns","cache-break-even-cost-curve/5 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 5 turns",68.89,"usd","$68.89","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","10 turns","cache-break-even-cost-curve/10 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 10 turns",76.71,"usd","$76.71","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.2 per M)","20 turns","cache-break-even-cost-curve/20 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 20 turns",92.37,"usd","$92.37","\u0001","\u0001","\u0001","1-hour cache write · read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","1 turn","cache-break-even-cost-curve/1 turn","Cost of a reused prefix with and without the cache, by session length (calculation): 1 turn",62.62,"usd","$62.62","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","2 turns","cache-break-even-cost-curve/2 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 2 turns",65.76,"usd","$65.76","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","3 turns","cache-break-even-cost-curve/3 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 3 turns",68.89,"usd","$68.89","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","5 turns","cache-break-even-cost-curve/5 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 5 turns",75.15,"usd","$75.15","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","10 turns","cache-break-even-cost-curve/10 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 10 turns",90.8,"usd","$90.80","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-cost-curve","Claude Opus 5.5 (1-hour cache write, read $0.4 per M)","20 turns","cache-break-even-cost-curve/20 turns","Cost of a reused prefix with and without the cache, by session length (calculation): 20 turns",122.12,"usd","$122.12","\u0001","\u0001","\u0001","1-hour cache write · read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","No cache (the same either way)","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-session-split/No cache (the same either way)","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (No cache (the same either way))",313.12,"usd","$313.12","\u0001","\u0001","\u0001","cache read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","No cache (the same either way)","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-session-split/No cache (the same either way)","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (No cache (the same either way))",313.12,"usd","$313.12","\u0001","\u0001","\u0001","cache read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","One 10-turn session, 1-hour cache","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-session-split/One 10-turn session, 1-hour cache","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (One 10-turn session, 1-hour cache)",76.71,"usd","$76.71","\u0001","\u0001","\u0001","cache read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","One 10-turn session, 1-hour cache","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-session-split/One 10-turn session, 1-hour cache","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (One 10-turn session, 1-hour cache)",90.8,"usd","$90.80","\u0001","\u0001","\u0001","cache read $0.4 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix)","Claude Opus 5.5 (cache read $0.2 per M)","cache-break-even-session-split/Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix)","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix))",626.24,"usd","$626.24","\u0001","\u0001","\u0001","cache read $0.2 per M",true,"\u0001","\u0001"],["prompt-cache-break-even","cache-break-even-session-split","Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix)","Claude Opus 5.5 (cache read $0.4 per M)","cache-break-even-session-split/Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix)","One 10-turn session or ten 1-turn sessions: cost with and without the cache (calculation) (Ten 1-turn sessions, 1-hour cache (assumed no reuse of the new prefix))",626.24,"usd","$626.24","\u0001","\u0001","\u0001","cache read $0.4 per M",true,"\u0001","\u0001"],["thinking-token-bill","thinking-bill-share","Median call","Claude Opus 5.5 · Claude Code","thinking-bill-share","Reasoning share of output tokens per call on hard tasks (calculation)",54.79,"percent","54.8%",24,"\u0001","minmax","Claude Code",true,[29.92,95.6],"none"],["thinking-token-bill","thinking-bill-share","Median call","Claude Opus 5.5 (high) · Claude Code","thinking-bill-share","Reasoning share of output tokens per call on hard tasks (calculation)",54.43,"percent","54.4%",24,"\u0001","minmax","Claude Code · effort high",true,[36.14,96.23],"none"],["thinking-token-bill","thinking-bill-cost-per-call","Reasoning (output tokens)","Claude Opus 5.5 (high) · Claude Code","thinking-bill-cost-per-call/Reasoning (output tokens)","List-price cost per call: reasoning, remaining output and input (calculation) (Reasoning (output tokens))",0.017969,"usd","$0.018",24,"\u0001","\u0001","Claude Code · effort high",true,"\u0001","none"],["thinking-token-bill","thinking-bill-cost-per-call","Reasoning (output tokens)","Claude Opus 5.5 · Claude Code","thinking-bill-cost-per-call/Reasoning (output tokens)","List-price cost per call: reasoning, remaining output and input (calculation) (Reasoning (output tokens))",0.012528,"usd","$0.013",24,"\u0001","\u0001","Claude Code",true,"\u0001","none"],["thinking-token-bill","thinking-bill-cost-per-call","Remaining output (visible-answer estimate)","Claude Opus 5.5 (high) · Claude Code","thinking-bill-cost-per-call/Remaining output (visible-answer estimate)","List-price cost per call: reasoning, remaining output and input (calculation) (Remaining output (visible-answer estimate))",0.00799,"usd","$0.0080",24,"\u0001","\u0001","Claude Code · effort high",true,"\u0001","none"],["thinking-token-bill","thinking-bill-cost-per-call","Remaining output (visible-answer estimate)","Claude Opus 5.5 · Claude Code","thinking-bill-cost-per-call/Remaining output (visible-answer estimate)","List-price cost per call: reasoning, remaining output and input (calculation) (Remaining output (visible-answer estimate))",0.008003,"usd","$0.0080",24,"\u0001","\u0001","Claude Code",true,"\u0001","none"],["thinking-token-bill","thinking-bill-cost-per-call","Input (prompt, cache priced)","Claude Opus 5.5 (high) · Claude Code","thinking-bill-cost-per-call/Input (prompt, cache priced)","List-price cost per call: reasoning, remaining output and input (calculation) (Input (prompt, cache priced))",0.007407,"usd","$0.0074",24,"\u0001","\u0001","Claude Code · effort high",true,"\u0001","none"],["thinking-token-bill","thinking-bill-cost-per-call","Input (prompt, cache priced)","Claude Opus 5.5 · Claude Code","thinking-bill-cost-per-call/Input (prompt, cache priced)","List-price cost per call: reasoning, remaining output and input (calculation) (Input (prompt, cache priced))",0.00771,"usd","$0.0077",24,"\u0001","\u0001","Claude Code",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Reasoning cost per strict pass","Claude Opus 5.5 (low) · Claude Code","thinking-bill-by-effort/Reasoning cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Reasoning cost per strict pass)",0.005031,"usd","$0.0050",16,"\u0001","\u0001","Claude Code · effort low",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Reasoning cost per strict pass","Claude Opus 5.5 (medium) · Claude Code","thinking-bill-by-effort/Reasoning cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Reasoning cost per strict pass)",0.01344,"usd","$0.013",16,"\u0001","\u0001","Claude Code · effort medium",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Reasoning cost per strict pass","Claude Opus 5.5 (high) · Claude Code","thinking-bill-by-effort/Reasoning cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Reasoning cost per strict pass)",0.018034,"usd","$0.018",16,"\u0001","\u0001","Claude Code · effort high",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Reasoning cost per strict pass","Claude Opus 5.5 · Claude Code","thinking-bill-by-effort/Reasoning cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Reasoning cost per strict pass)",0.013104,"usd","$0.013",16,"\u0001","\u0001","Claude Code",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Total cost per strict pass","Claude Opus 5.5 (low) · Claude Code","thinking-bill-by-effort/Total cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Total cost per strict pass)",0.021152,"usd","$0.021",16,"\u0001","\u0001","Claude Code · effort low",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Total cost per strict pass","Claude Opus 5.5 (medium) · Claude Code","thinking-bill-by-effort/Total cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Total cost per strict pass)",0.029475,"usd","$0.029",16,"\u0001","\u0001","Claude Code · effort medium",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Total cost per strict pass","Claude Opus 5.5 (high) · Claude Code","thinking-bill-by-effort/Total cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Total cost per strict pass)",0.033677,"usd","$0.034",16,"\u0001","\u0001","Claude Code · effort high",true,"\u0001","none"],["thinking-token-bill","thinking-bill-by-effort","Total cost per strict pass","Claude Opus 5.5 · Claude Code","thinking-bill-by-effort/Total cost per strict pass","Reasoning cost per strict pass by effort, with the total (calculation) (Total cost per strict pass)",0.028925,"usd","$0.029",16,"\u0001","\u0001","Claude Code",true,"\u0001","none"],["thinking-token-bill","thinking-bill-short-vs-hard","Eight hard tasks","Claude Opus 5.5 · Claude Code","thinking-bill-short-vs-hard/Eight hard tasks","Reasoning share on short tasks vs hard tasks (calculation) (Eight hard tasks)",54.79,"percent","54.8%",24,"\u0001","minmax","Claude Code",true,[29.92,95.6],"none"],["thinking-token-bill","thinking-bill-short-vs-hard","Eight hard tasks","Claude Opus 5.5 (high) · Claude Code","thinking-bill-short-vs-hard/Eight hard tasks","Reasoning share on short tasks vs hard tasks (calculation) (Eight hard tasks)",54.43,"percent","54.4%",24,"\u0001","minmax","Claude Code · effort high",true,[36.14,96.23],"none"],["thinking-token-bill","thinking-bill-short-vs-hard","Five short tasks","Claude Opus 5.5 · Claude Code","thinking-bill-short-vs-hard/Five short tasks","Reasoning share on short tasks vs hard tasks (calculation) (Five short tasks)",0,"percent","0%",15,"\u0001","minmax","Claude Code",true,[0,93.33],"none"],["thinking-token-bill","thinking-bill-short-vs-hard","Five short tasks","Claude Opus 5.5 (high) · Claude Code","thinking-bill-short-vs-hard/Five short tasks","Reasoning share on short tasks vs hard tasks (calculation) (Five short tasks)",43.59,"percent","43.6%",15,"\u0001","minmax","Claude Code · effort high",true,[0,93.33],"none"],["llm-speed-anatomy","speed-anatomy-first-text","Time to first text","Claude Opus 5.5 · Claude Code","speed-anatomy-first-text","Time to first text: a 250-line answer, six models",1.97,"seconds","1.97 s",4,"\u0001","minmax","Claude Code","\u0001",[1.7,2.35],"\u0001"],["llm-speed-anatomy","speed-anatomy-output-speed","Visible tokens per second","Claude Opus 5.5 · Claude Code","speed-anatomy-output-speed","Output speed after the first text: visible tokens per second (calculation)",155.5,"tokens","156",4,"\u0001","minmax","Claude Code",true,[154.6,156.4],"\u0001"],["llm-speed-anatomy","speed-anatomy-chars-per-second","Characters per second","Claude Opus 5.5 · Claude Code","speed-anatomy-chars-per-second","Output speed in characters per second after the first text (calculation)",347,"count","347",4,"\u0001","minmax","Claude Code",true,[345,349],"\u0001"],["llm-speed-anatomy","speed-anatomy-prompt-size","Claude Opus 5.5 · Claude Code","1k","speed-anatomy-prompt-size/1k","Time to first text as the prompt grows: 1k",1.51,"seconds","1.51 s",3,"\u0001","minmax","Claude Code",true,[1.46,2.01],"\u0001"],["llm-speed-anatomy","speed-anatomy-prompt-size","Claude Opus 5.5 · Claude Code","16k","speed-anatomy-prompt-size/16k","Time to first text as the prompt grows: 16k",1.74,"seconds","1.74 s",3,"\u0001","minmax","Claude Code",true,[1.7,2.97],"\u0001"],["llm-speed-anatomy","speed-anatomy-prompt-size","Claude Opus 5.5 · Claude Code","64k","speed-anatomy-prompt-size/64k","Time to first text as the prompt grows: 64k",1.79,"seconds","1.79 s",3,"\u0001","minmax","Claude Code",true,[1.72,3.72],"\u0001"],["llm-speed-anatomy","speed-anatomy-total-by-size","1k prompt","Claude Opus 5.5 · Claude Code","speed-anatomy-total-by-size/1k prompt","Total time per call by prompt size (1k prompt)",1.83,"seconds","1.83 s",3,"\u0001","minmax","Claude Code","\u0001",[1.82,2.41],"\u0001"],["llm-speed-anatomy","speed-anatomy-total-by-size","16k prompt","Claude Opus 5.5 · Claude Code","speed-anatomy-total-by-size/16k prompt","Total time per call by prompt size (16k prompt)",2.36,"seconds","2.36 s",3,"\u0001","minmax","Claude Code","\u0001",[2.11,3.4],"\u0001"],["llm-speed-anatomy","speed-anatomy-total-by-size","64k prompt","Claude Opus 5.5 · Claude Code","speed-anatomy-total-by-size/64k prompt","Total time per call by prompt size (64k prompt)",2.35,"seconds","2.35 s",3,"\u0001","minmax","Claude Code","\u0001",[2.26,4.29],"\u0001"],["llm-speed-anatomy","speed-anatomy-lookup-correct","Exact answer","Claude Opus 5.5 · Claude Code","speed-anatomy-lookup-correct","Exact lookup answers at the 1k, 16k and 64k prompt-size targets",0.5556,"rate","56% (5/9)",9,[0.2667,0.8112],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-pass-rate","Strict pass","Claude Opus 5.5 · Claude Code","harder-h2h-pass-rate/Strict pass","Pass rate on 4 harder tasks (Strict pass)",0.4167,"rate","42% (5/12)",12,[0.1933,0.6805],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-pass-rate","Lenient (format misses counted)","Claude Opus 5.5 · Claude Code","harder-h2h-pass-rate/Lenient (format misses counted)","Pass rate on 4 harder tasks (Lenient (format misses counted))",0.5,"rate","50% (6/12)",12,[0.2538,0.7462],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-tool-attempts","Tool attempt","Claude Opus 5.5 · Claude Code","harder-h2h-tool-attempts","Calls that tried a tool although tools were off",0.4167,"rate","42% (5/12)",12,[0.1933,0.6805],"ci95","Claude Code","\u0001","\u0001","none"],["harder-tasks-head-to-head","harder-h2h-pass-by-task","Claude Opus 5.5 · Claude Code","10x10 nonogram","harder-h2h-pass-by-task/10x10 nonogram","Strict pass rate by task: 10x10 nonogram",1,"rate","100% (3/3)",3,[0.4385,1],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-pass-by-task","Claude Opus 5.5 · Claude Code","Sudoku, 22 givens","harder-h2h-pass-by-task/Sudoku, 22 givens","Strict pass rate by task: Sudoku, 22 givens",0,"rate","0% (0/3)",3,[0,0.5615],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-pass-by-task","Claude Opus 5.5 · Claude Code","6x6 Skyscrapers","harder-h2h-pass-by-task/6x6 Skyscrapers","Strict pass rate by task: 6x6 Skyscrapers",0.3333,"rate","33% (1/3)",3,[0.0615,0.7923],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-pass-by-task","Claude Opus 5.5 · Claude Code","Seeded shuffle output","harder-h2h-pass-by-task/Seeded shuffle output","Strict pass rate by task: Seeded shuffle output",0.3333,"rate","33% (1/3)",3,[0.0615,0.7923],"ci95","Claude Code","\u0001","\u0001","higher"],["harder-tasks-head-to-head","harder-h2h-total-latency","Total time per call","Claude Opus 5.5 · Claude Code","harder-h2h-total-latency","Total time per call on harder tasks",80.34,"seconds","80.3 s",9,"\u0001","minmax","Claude Code","\u0001",[3.82,279.5],"\u0001"],["harder-tasks-head-to-head","harder-h2h-output-tokens","Output tokens","Claude Opus 5.5 · Claude Code","harder-h2h-output-tokens/Output tokens","Output tokens per call on harder tasks (Output tokens)",8420,"tokens","8,420",9,"\u0001","minmax","Claude Code","\u0001",[279,40044],"none"],["harder-tasks-head-to-head","harder-h2h-cost-per-pass","Cost per strict pass","Claude Opus 5.5 · Claude Code","harder-h2h-cost-per-pass","List-price cost per strict pass on harder tasks (calculation)",0.59333,"usd","$0.59",12,"\u0001","\u0001","Claude Code",true,"\u0001","\u0001"]]}