MiMo-V2.6-Flash
Task results
Task catalog ↗| Task | Hardware | Agent | Provider | Trajectory | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| agentic-search | CPU | Codex | OpenRouter | 11.7 | 1h 54min | 31,136,619 | 93,416 | 30,654,688 | $0.18 | Trace → |
| agentic-search-vectorless | CPU | Codex | OpenRouter | 0.0 | 45min | 1,396,039 | 405,674 | 698,023 | $0.21 | Trace → |
| biomedical-graph-retrieval | CPU | Codex | OpenRouter | 0.0 | 14min | 2,723,346 | 28,329 | 2,314,624 | $0.07 | Trace → |
| budgeted-bimetric-retrieval | CPU | Codex | OpenRouter | 0.0 | 18min | 9,687,619 | 40,195 | 9,430,336 | $0.07 | Trace → |
| code-context-retrieval | CPU | Codex | OpenRouter | 1.6 | 54min | 15,242,970 | 55,220 | 14,164,672 | $0.21 | Trace → |
| evolving-personal-memory | CPU | Codex | OpenRouter | 8.2 | 31min | 4,616,822 | 311,520 | 3,666,760 | $0.23 | Trace → |
| filtered-ann-retrieval | CPU | Codex | OpenRouter | 0.0 | 48min | 13,615,175 | 168,517 | 12,797,536 | $0.20 | Trace → |
| financial-report-qa | CPU | Codex | OpenRouter | 6.9 | 50min | 9,258,454 | 42,876 | 8,808,960 | $0.10 | Trace → |
| icsi-meeting-memory | CPU | Codex | OpenRouter | 0.0 | 57min | 12,708,858 | 79,085 | 12,530,816 | $0.08 | Trace → |
| incremental-vector-search | CPU | Codex | OpenRouter | 0.7 | 1h 59min | 84,985,689 | 152,799 | 84,499,712 | $0.35 | Trace → |
| join-aware-table-retrieval | CPU | Codex | OpenRouter | 20.0 | 50min | 14,599,290 | 68,878 | 14,375,936 | $0.09 | Trace → |
| large-scale-formula-retrieval | CPU | Codex | OpenRouter | 0.0 | 24min | 5,012,098 | 47,959 | 4,635,008 | $0.08 | Trace → |
| long-document-reranking | CPU | Codex | OpenRouter | 0.0 | 7min | 4,031,943 | 108,053 | 3,435,264 | $0.12 | Trace → |
| long-pdf-evidence | CPU | Codex | OpenRouter | 0.0 | 57min | 15,085,918 | 71,130 | 14,762,816 | $0.11 | Trace → |
| long-pdf-evidence-vectorless | CPU | Codex | OpenRouter | 0.0 | 56min | 14,690,336 | 106,377 | 14,490,112 | $0.10 | Trace → |
| memory-constrained-dense-retrieval | CPU | Codex | OpenRouter | 0.0 | 20min | 4,519,132 | 59,604 | 4,021,280 | $0.10 | Trace → |
| narrative-clue-search | CPU | Codex | OpenRouter | 8.2 | 21min | 3,223,959 | 103,050 | 2,674,304 | $0.11 | Trace → |
| negative-constraint-retrieval | CPU | Codex | OpenRouter | 20.0 | 1h 25min | 14,224,750 | 459,548 | 10,656,315 | $0.66 | Trace → |
| paper-metadata-retrieval | CPU | Codex | OpenRouter | 0.0 | 33min | 8,763,566 | 42,944 | 8,402,816 | $0.09 | Trace → |
| reasoning-query-rewriting | CPU | Codex | OpenRouter | 10.0 | 2h 0min | 27,023,822 | 621,378 | 19,763,424 | $1.25 | Trace → |
| rust-bm25-search | CPU | Codex | OpenRouter | 0.0 | 17min | 6,010,975 | 50,346 | 5,732,736 | $0.07 | Trace → |
| scientific-paper-qa | CPU | Codex | OpenRouter | 20.0 | 2h 0min | 16,093,014 | 592,360 | 11,906,816 | $0.79 | Trace → |
| sparse-retrieval-pruning | CPU | Codex | OpenRouter | 0.0 | 55min | 3,900,004 | 532,904 | 2,453,150 | $0.36 | Trace → |
| visual-document-qa | CPU | Codex | OpenRouter | 6.8 | 23min | 6,722,315 | 31,152 | 6,460,608 | $0.06 | Trace → |
| budgeted-candidate-reranking | GPU | Codex | OpenRouter | 0.0 | 14min | 4,662,967 | 25,651 | 4,449,152 | $0.05 | Trace → |
| chunqiu-temporal-retrieval | GPU | Codex | OpenRouter | 0.0 | 25min | 4,497,978 | 42,559 | 4,202,688 | $0.07 | Trace → |
| code-embedding-finetuning | GPU | Codex | OpenRouter | 0.0 | 1h 30min | 2,968,279 | 548,063 | 696,721 | $0.47 | Trace → |
| code-reranker-finetuning | GPU | Codex | OpenRouter | 25.0 | 1h 17min | 15,602,013 | 126,135 | 12,112,320 | $0.56 | Trace → |
| composed-image-search | GPU | Codex | OpenRouter | 0.0 | 12min | 1,540,080 | 47,093 | 1,252,928 | $0.06 | Trace → |
| constrained-molecular-search | GPU | Codex | OpenRouter | 8.1 | 11min | 2,470,192 | 50,146 | 2,084,288 | $0.07 | Trace → |
| decision-model-training | GPU | Codex | OpenRouter | 0.0 | 39min | 5,307,875 | 51,768 | 4,997,440 | $0.07 | Trace → |
| document-page-search | GPU | Codex | OpenRouter | 3.9 | 1h 0min | 15,378,494 | 68,930 | 14,976,581 | $0.12 | Trace → |
| instruction-following-embedding | GPU | Codex | OpenRouter | 0.0 | 54min | 29,272,393 | 247,837 | 26,020,672 | $0.60 | Trace → |
| khmer-embedding-training | GPU | Codex | OpenRouter | 17.7 | 1h 14min | 5,432,770 | 51,356 | 5,250,688 | $0.05 | Trace → |
| layout-page-search | GPU | Codex | OpenRouter | 0.0 | 13min | 1,626,764 | 54,219 | 1,312,768 | $0.06 | Trace → |
| legal-stance-retrieval | GPU | Codex | OpenRouter | 0.0 | 25min | 6,753,628 | 58,912 | 5,787,168 | $0.17 | Trace → |
| lightweight-query-retrieval | GPU | Codex | OpenRouter | 0.0 | 51min | 8,469,696 | 39,322 | 7,640,288 | $0.15 | Trace → |
| methodology-inspiration-retrieval | GPU | Codex | OpenRouter | 0.0 | 32min | 8,005,801 | 46,125 | 7,370,976 | $0.12 | Trace → |
| multilingual-vector-postprocessing | GPU | Codex | OpenRouter | 20.1 | 23min | 5,413,804 | 33,353 | 4,773,184 | $0.11 | Trace → |
| protein-text-bidirectional-retrieval | GPU | Codex | OpenRouter | 0.0 | 45min | 5,324,621 | 27,579 | 4,135,150 | $0.19 | Trace → |
| quantity-aware-retrieval | GPU | Codex | OpenRouter | 0.0 | 9min | 1,714,594 | 17,847 | 1,460,576 | $0.04 | Trace → |
| query-encoder-alignment | GPU | Codex | OpenRouter | 0.0 | 1min | 256,974 | 4,129 | 164,672 | $0.01 | Trace → |
| same-place-image-search | GPU | Codex | OpenRouter | 0.0 | 8min | 743,896 | 11,141 | 698,880 | $0.01 | Trace → |
| sketch-text-search | GPU | Codex | OpenRouter | 1.4 | 1h 52min | 20,011,474 | 88,443 | 19,133,632 | $0.20 | Trace → |
| spoken-query-search | GPU | Codex | OpenRouter | 2.0 | 2h 0min | 25,674,079 | 534,300 | 22,962,322 | $0.59 | Trace → |
| training-error-tracing | GPU | Codex | OpenRouter | 20.0 | 40min | 18,824,905 | 56,478 | 17,373,891 | $0.27 | Trace → |
| video-moment-search | GPU | Codex | OpenRouter | 10.9 | 16min | 2,668,851 | 30,250 | 2,585,152 | $0.03 | Trace → |
No matching tasks. Try a different search.
47 selected evaluations · valid zero scores included
Score: task reward × 100. Tokens: coding usage; cached tokens are included in input.
Cost is estimated from recorded agent tokens at official API rates in USD (2026-11-01; DeepSeek off-peak pricing).