tb21-diagnostic-heredoc-brief-max-margin-probe-0930-daytona-20260805-074514 | terminal-bench/terminal-bench-2-1 | 14/39 | shaun smith | 5 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard01-20260805-062609 | terminal-bench/terminal-bench-2-1 | 55/55 | shaun smith | 0 | 8/5/26 |
tb21-diagnostic-small-steps-probe-0930-daytona-20260805-051907 | terminal-bench/terminal-bench-2-1 | 39/39 | shaun smith | 11 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard07-20260805-043501 | terminal-bench/terminal-bench-2-1 | 45/45 | shaun smith | 2 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-local-shard01-20260805-043501 | terminal-bench/terminal-bench-2-1 | 5/5 | shaun smith | 0 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard02-20260805-030806 | terminal-bench/terminal-bench-2-1 | 55/55 | shaun smith | 7 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-local-shard04-20260805-030806 | terminal-bench/terminal-bench-2-1 | 5/5 | shaun smith | 0 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard04-20260805-015737 | terminal-bench/terminal-bench-2-1 | 55/55 | shaun smith | 3 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-local-shard03-20260805-015737 | terminal-bench/terminal-bench-2-1 | 5/5 | shaun smith | 0 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard06-20260804-235850 | terminal-bench/terminal-bench-2-1 | 55/55 | shaun smith | 5 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-local-shard05-20260804-235850 | terminal-bench/terminal-bench-2-1 | 5/5 | shaun smith | 1 | 8/5/26 |
tb21-grok45-high-c6-r3-s300-0100-daytona-shard08-20260804-213358 | terminal-bench/terminal-bench-2-1 | 45/45 | shaun smith | 8 | 8/4/26 |
tb21-grok45-high-c6-r3-s300-0100-local-shard02-20260804-213358 | terminal-bench/terminal-bench-2-1 | 5/5 | shaun smith | 0 | 8/4/26 |
tb21-deepseek-v4-flash-max-heredoc-r3-t1p095-c22-0930-local-20260804-191545 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 8/4/26 |
tb21-deepseek-v4-flash-max-heredoc-r3-t1p095-c22-0930-daytona-20260804-191523 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 104 | 8/4/26 |
tb21-deepseek-v4-flash-high-heredoc-r1-t1p095-c22-0930-local-20260804-190509 | terminal-bench/terminal-bench-2-1 | 0/25 | shaun smith | 0 | 8/4/26 |
tb21-deepseek-v4-flash-high-heredoc-r1-t1p095-c22-0930-daytona-20260804-190455 | terminal-bench/terminal-bench-2-1 | 11/420 | shaun smith | 7 | 8/4/26 |
tb21-diagnostic-heredoc-guidance-probe-0930-daytona-20260804-163342 | terminal-bench/terminal-bench-2-1 | 49/60 | shaun smith | 30 | 8/4/26 |
tb21-deepseek-v4-flash-high-r1-t1p095-c22-0930-replacement-20260804-061719-b | terminal-bench/terminal-bench-2-1 | 4/4 | shaun smith | 2 | 8/4/26 |
tb21-deepseek-v4-flash-high-r1-t1p095-c22-0930-replacement-20260804-061719-a | terminal-bench/terminal-bench-2-1 | 14/14 | shaun smith | 6 | 8/4/26 |
tb21-deepseek-v4-flash-high-r1-t1p095-c22-0930-daytona-20260803-121512 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 94 | 8/3/26 |
tb21-deepseek-v4-flash-high-r1-t1p095-c22-0930-local-20260803-121500 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 8/3/26 |
tb21-deepseek-v4-flash-high-r1-t1p095-c22-0930-local-20260803-120814 | terminal-bench/terminal-bench-2-1 | 0/25 | shaun smith | 0 | 8/3/26 |
tb21-diagnostic-deepseek-r3-long2x-nocompact-probe12-0930-daytona-20260803-065248 | terminal-bench/terminal-bench-2-1 | 12/12 | shaun smith | 3 | 8/3/26 |
tb21-diagnostic-deepseek-v4-flash-max-r3-long2x-timeout32-0930-daytona-20260802-224246 | terminal-bench/terminal-bench-2-1 | 160/160 | shaun smith | 44 | 8/2/26 |
tb21-sol-max-r6-0930-daytona-20260802-212136 | terminal-bench/terminal-bench-2-1 | 51/420 | shaun smith | 14 | 8/2/26 |
tb21-sol-max-r6-0930-local-20260802-212113 | terminal-bench/terminal-bench-2-1 | 9/25 | shaun smith | 2 | 8/2/26 |
tb21-deepseek-v4-flash-max-r4-turn75-t1p095-c22-0930-daytona-20260802-120941 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 81 | 8/2/26 |
tb21-deepseek-v4-flash-max-r4-turn75-t1p095-c22-0930-local-20260802-120932 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 1 | 8/2/26 |
tb21-deepseek-v4-flash-max-r3-t1p095-c22-0930-daytona-20260801-222647 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 96 | 8/1/26 |
tb21-deepseek-v4-flash-max-r3-t1p095-c22-0930-local-20260801-222647 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 8/1/26 |
tb21-deepseek-v4-flash-max-r2-c22-0930-local-20260801-221112 | terminal-bench/terminal-bench-2-1 | 2/25 | shaun smith | 1 | 8/1/26 |
tb21-deepseek-v4-flash-max-r2-c22-0930-daytona-20260801-220532 | terminal-bench/terminal-bench-2-1 | 13/420 | shaun smith | 8 | 8/1/26 |
tb21-deepseek-v4-flash-max-r1-0930-daytona-20260801-092535 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 80 | 8/1/26 |
tb21-deepseek-v4-flash-max-r1-0930-local-20260801-092515 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 8/1/26 |
tb21-sol-max-r5-0930-daytona-20260801-091805 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 40 | 8/1/26 |
tb21-sol-max-r5-0930-local-20260801-091751 | terminal-bench/terminal-bench-2-1 | 20/25 | shaun smith | 0 | 8/1/26 |
tb21-luna-max-flex-r3-0929-daytona-20260731-203433 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 16 | 7/31/26 |
tb21-luna-max-flex-r3-0929-local-20260731-203419 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 7/31/26 |
tb21-luna-max-flex-r2-0928-daytona-20260731-113527 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 23 | 7/31/26 |
tb21-luna-max-flex-r2-0928-local-20260731-113521 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 7/31/26 |
tb21-luna-max-flex-r1-0928-daytona-20260731-071414 | terminal-bench/terminal-bench-2-1 | 222/420 | shaun smith | 17 | 7/31/26 |
tb21-luna-max-flex-r1-0928-local-20260731-071259 | terminal-bench/terminal-bench-2-1 | 2/25 | shaun smith | 2 | 7/31/26 |
tb21-luna-max-flex-r1-0928-local-20260731-071252 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 7/31/26 |
tb21-glm52-zai-max-calibration15-0927-daytona-20260729-152449 | terminal-bench/terminal-bench-2-1 | 15/15 | shaun smith | 5 | 7/29/26 |
tb21-sol-low-r1-0926-daytona-20260728-140400 | terminal-bench/terminal-bench-2-1 | 420/420 | shaun smith | 4 | 7/28/26 |
tb21-sol-low-r1-0926-local-20260728-140354 | terminal-bench/terminal-bench-2-1 | 25/25 | shaun smith | 0 | 7/28/26 |
tb21-sol-low-r1-0926-daytona-20260728-135841 | terminal-bench/terminal-bench-2-1 | 9/420 | shaun smith | 8 | 7/28/26 |
tb21-sol-low-r1-0926-local-20260728-135841 | terminal-bench/terminal-bench-2-1 | 0/25 | shaun smith | 0 | 7/28/26 |
tb21-glm52-max-calibration15-0926-daytona-20260728-095715 | terminal-bench/terminal-bench-2-1 | 15/15 | shaun smith | 6 | 7/28/26 |