Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 0.5349 | $1954.03 | 921.6M | 1.6M | 19h 56m | 1932 | 31 |
| 2 | Gemini 4 Argon | 0.4359 | $139.21 | 309.9M | 955k | 8h 57m | 746 | 6 |
| 3 | Claude Sonnet 5.5 | 0.3720 | $144.95 | 566.2M | 2.4M | 18h 50m | 1343 | 11 |
| 4 | Claude Haiku 5.5 | 0.1173 | $15.92 | 254.5M | 1.2M | 10h 40m | 625 | 2 |
| 5 | Muse Spark 1.3 | 0.1159 | $180.28 | 204.8M | 347k | 10h 27m | 670 | 14 |
| 6 | GPT-5.6 Sol | 0.1092 | $291.23 | 284.1M | 251k | 5h 12m | 616 | 12 |
| 7 | GPT-5.6 Sol | 0.0675 | $443.00 | 437.3M | 281k | 6h 23m | 877 | 14 |
| 8 | Grok 4.7 | 0.0552 | $802.99 | 801.5M | 2.3M | 19h 22m | 3183 | 24 |
| 9 | GLM-5.3 | 0.0534 | $68.77 | 241.2M | 448k | 15h 36m | 650 | 8 |
| 10 | Muse Spark 1.2 | 0.0532 | $132.47 | 498.4M | 1.4M | 17h 13m | 1444 | 3 |
| 11 | Claude Fable 5 | 0.0442 | $246.50 | 205.1M | 519k | 8h 17m | 481 | 10 |
| 12 | Grok 4.6 | 0.0322 | $488.14 | 454.2M | 2.3M | 19h 33m | 1703 | 83 |
| 13 | Claude Opus 5 | 0.0249 | $124.87 | 207.2M | 534k | 12h 23m | 460 | 7 |
| 14 | Qwen3.8-Max-0902 | 0.0242 | $30.19 | 91.7M | 767k | 20h 6m | 434 | 1 |
| 15 | Claude Opus 5 | 0.0223 | $101.43 | 161.0M | 523k | 12h 35m | 390 | 8 |
| 16 | Qwen3.8-Max | 0.0214 | $45.80 | 153.5M | 1.1M | 15h 59m | 715 | 7 |
| 17 | GLM-5.3 | 0.0211 | $67.37 | 244.9M | 383k | 14h 17m | 698 | 20 |
| 18 | Gemini 3.8 Flash | 0.0190 | $30.46 | 330.6M | 252k | 3h 24m | 709 | 11 |
| 19 | Gemini 3.7 Flash | 0.0169 | $19.15 | 195.9M | 289k | 3h 33m | 505 | 4 |
| 20 | GPT-5.6 Sol | 0.0168 | $283.36 | 279.0M | 247k | 6h 47m | 655 | 21 |
| 21 | Kimi K3 | 0.0103 | $110.14 | 311.1M | 507k | 20h 1m | 740 | 11 |
| 22 | Muse Spark 1.2 | 0.0099 | $100.58 | 403.5M | 1.7M | 11h 46m | 1193 | 8 |
| 23 | Muse Spark 1.2 | 0.0081 | $15.03 | 90.2M | 152k | 1h 36m | 211 | 7 |
| 24 | Qwen3.8-Max | 0.0081 | $33.42 | 99.7M | 1.3M | 15h 1m | 574 | 8 |
| 25 | Gemini 3.8 Flash | 0.0058 | $23.48 | 261.8M | 192k | 2h 8m | 563 | 4 |
| 26 | Claude Opus 5 | 0.0048 | $110.39 | 179.3M | 515k | 12h 40m | 431 | 7 |
| 27 | Muse Spark 1.2 | 0.0047 | $67.55 | 167.8M | 657k | 12h 12m | 541 | 6 |
| 28 | Grok 4.6 | 0.0025 | $162.38 | 158.0M | 937k | 10h 27m | 649 | 14 |
| 29 | Gemini 3.8 Flash | 0.0021 | $39.53 | 434.9M | 429k | 7h 2m | 1119 | 13 |
| 30 | Grok 4.6 | 0.0012 | $313.02 | 296.5M | 1.9M | 18h 41m | 1120 | 19 |
| 31 | Qwen3.8-Max-0902 | 0.0009 | $28.62 | 81.5M | 1.2M | 20h 5m | 391 | 1 |
| 32 | Qwen3.8-Max-0902 | 0.0009 | $26.00 | 76.8M | 998k | 20h 6m | 387 | 2 |
| 33 | Grok 4.6 | 0.0007 | $96.00 | 91.3M | 481k | 3h 53m | 329 | 3 |
| 34 | Qwen3.8-Max | 0.0004 | $47.32 | 149.7M | 1.5M | 17h 59m | 651 | 3 |
| 35 | GLM-5.3 | 0.0004 | $46.58 | 170.2M | 369k | 10h 37m | 591 | 7 |
| 36 | Claude Haiku 5.5 | 0.0000 | $14.49 | 235.4M | 958k | 9h 43m | 594 | 3 |
| 37 | Claude Haiku 5.5 | 0.0000 | $14.92 | 236.6M | 1.1M | 7h 37m | 597 | 2 |
| 38 | Claude Opus 5.5 | 0.0000 | $159.94 | 559.4M | 1.8M | 19h 25m | 1329 | 26 |
| 39 | Claude Fable 5 | 0.0000 | $202.86 | 169.0M | 429k | 14h 47m | 436 | 14 |
| 40 | GLM-5.3 | 0.0000 | $50.83 | 180.8M | 386k | 12h 52m | 576 | 4 |
| 41 | Claude Fable 5.1 | 0.0000 | $219.62 | 392.8M | 963k | 7h 58m | 844 | 9 |
| 42 | Muse Spark 1.2 | 0.0000 | $32.81 | 65.0M | 127k | 4h 50m | 276 | 3 |
| 43 | Claude Fable 5.1 | 0.0000 | $193.70 | 342.2M | 936k | 9h 59m | 820 | 11 |
| 44 | DeepSeek V4 Flash Vision Exp | 0.0000 | $2.44 | 138.4M | 299k | 9h 52m | 531 | 4 |
| 45 | Claude Haiku 5.5 | 0.0000 | $13.92 | 215.0M | 1.1M | 9h 1m | 513 | 3 |
| 46 | DeepSeek V4 Flash Vision Exp | 0.0000 | $5.46 | 332.4M | 492k | 10h 53m | 782 | 15 |
| 47 | Grok 4.7 | 0.0000 | $211.95 | 219.1M | 541k | 7h 14m | 876 | 5 |
| 48 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.59 | 206.9M | 443k | 9h 31m | 593 | 16 |
| 49 | Claude Opus 5.5 | 0.0000 | $183.76 | 644.5M | 2.0M | 19h 7m | 1476 | 23 |
| 50 | Gemini 4 Argon | 0.0000 | $275.58 | 621.4M | 1.5M | 15h 16m | 1391 | 22 |
| 51 | Kimi K3 | 0.0000 | $185.83 | 517.0M | 1.5M | 20h 0m | 1188 | 13 |
| 52 | GPT-6 Astra | 0.0000 | $2665.44 | 1249.7M | 2.4M | 19h 33m | 2699 | 42 |
| 53 | GPT-5.6 Sol | 0.0000 | $109.76 | 114.5M | 139k | 5h 57m | 401 | 7 |
| 54 | Claude Sonnet 5.5 | 0.0000 | $131.29 | 505.6M | 2.3M | 19h 12m | 1248 | 7 |
| 55 | Grok 4.7 | 0.0000 | $51.59 | 50.1M | 157k | 1h 43m | 212 | 5 |
| 56 | Gemini 4 Argon | 0.0000 | $100.53 | 344.7M | 936k | 8h 35m | 828 | 8 |
| 57 | Gemini 3.8 Flash | 0.0000 | $24.27 | 258.5M | 198k | 4h 49m | 607 | 3 |
| 58 | GLM-5.3 Flash | 0.0000 | $3.26 | 101.7M | 249k | 9h 20m | 478 | 7 |
| 59 | Claude Opus 5.5 | 0.0000 | $185.38 | 644.4M | 2.1M | 18h 30m | 1447 | 29 |
| 60 | Claude Opus 5 | 0.0000 | $89.33 | 141.7M | 467k | 15h 55m | 376 | 11 |
| 61 | Inkling | 0.0000 | $4.87 | 5.1M | 12k | 1h 40m | 92 | 3 |
| 62 | Grok 4.7 | 0.0000 | $100.20 | 104.5M | 326k | 3h 50m | 470 | 5 |
| 63 | Claude Fable 5.1 | 0.0000 | $177.26 | 316.2M | 794k | 11h 11m | 833 | 9 |
| 64 | Gemini 4 Argon | 0.0000 | $197.19 | 445.3M | 1.3M | 12h 41m | 1022 | 9 |
| 65 | Kimi K3 | 0.0000 | $246.45 | 710.4M | 1.8M | 20h 0m | 1736 | 14 |
| 66 | Gemini 3.8 Flash | 0.0000 | $21.47 | 225.2M | 181k | 2h 13m | 571 | 5 |
| 67 | Muse Spark 1.3 | 0.0000 | $429.35 | 454.7M | 706k | 19h 28m | 1165 | 8 |
| 68 | Claude Haiku 5.5 | 0.0000 | $24.57 | 393.7M | 1.7M | 13h 34m | 905 | 6 |
| 69 | Grok 4.7 | 0.0000 | $565.89 | 566.8M | 1.5M | 11h 16m | 2189 | 10 |
| 70 | GLM-5.3 | 0.0000 | $68.85 | 206.5M | 390k | 14h 23m | 607 | 17 |
| 71 | Claude Sonnet 5.5 | 0.0000 | $90.56 | 360.5M | 1.4M | 18h 46m | 879 | 8 |
| 72 | Inkling | 0.0000 | $7.60 | 8.0M | 10k | 1h 46m | 120 | 2 |
| 73 | Gemini 3.7 Flash | 0.0000 | $9.47 | 100.2M | 149k | 1h 43m | 316 | 4 |
| 74 | Muse Spark 1.3 | 0.0000 | $58.36 | 60.2M | 197k | 8h 23m | 386 | 3 |
| 75 | GPT-5.6 Sol | 0.0000 | $182.18 | 175.0M | 189k | 6h 4m | 485 | 8 |
| 76 | Inkling | 0.0000 | $5.18 | 5.4M | 12k | 1h 28m | 91 | 2 |
| 77 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.41 | 198.5M | 360k | 8h 1m | 562 | 4 |
| 78 | Claude Opus 5.5 | 0.0000 | $134.68 | 471.5M | 1.5M | 18h 23m | 1059 | 21 |
| 79 | Grok 4.6 | 0.0000 | $419.76 | 405.9M | 2.2M | 19h 4m | 1586 | 60 |
| 80 | GPT-6 Astra | 0.0000 | $2441.52 | 1153.7M | 2.1M | 19h 6m | 2553 | 41 |
| 81 | Claude Fable 5.1 | 0.0000 | $182.53 | 329.2M | 746k | 9h 31m | 841 | 21 |
| 82 | GPT-6 Astra | 0.0000 | $2574.70 | 1208.7M | 2.3M | 17h 31m | 2622 | 65 |
| 83 | GLM-5.3 Flash | 0.0000 | $5.76 | 124.8M | 287k | 14h 48m | 473 | 3 |
| 84 | Claude Opus 5.5 | 0.0000 | $150.29 | 514.2M | 1.7M | 17h 0m | 1206 | 15 |
| 85 | Inkling | 0.0000 | $6.42 | 6.7M | 16k | 1h 12m | 100 | 1 |
| 86 | DeepSeek V4 Flash Vision Exp | 0.0000 | $3.54 | 209.2M | 364k | 8h 32m | 632 | 9 |
| 87 | GPT-6 Astra | 0.0000 | $1722.33 | 819.7M | 1.5M | 19h 18m | 1844 | 42 |
| 88 | Qwen3.8-Max | 0.0000 | $42.20 | 143.0M | 952k | 17h 51m | 604 | 1 |
| 89 | Kimi K3 | 0.0000 | $49.64 | 141.5M | 328k | 6h 19m | 529 | 7 |
| 90 | Inkling | 0.0000 | $14.76 | 15.4M | 36k | 34m | 194 | 2 |
| 91 | Claude Sonnet 5.5 | 0.0000 | $128.12 | 516.0M | 1.9M | 18h 29m | 1195 | 8 |
| 92 | Gemini 3.7 Flash | 0.0000 | $9.02 | 85.7M | 143k | 1h 52m | 306 | 1 |
| 93 | Gemini 4 Argon | 0.0000 | $160.21 | 500.1M | 1.5M | 13h 56m | 1169 | 20 |
| 94 | Claude Fable 5 | 0.0000 | $289.82 | 249.1M | 515k | 7h 2m | 543 | 12 |
| 95 | GLM-5.3 Flash | 0.0000 | $3.52 | 102.4M | 346k | 8h 20m | 418 | 2 |
| 96 | Qwen3.8-Max | 0.0000 | $47.25 | 152.8M | 1.4M | 17h 10m | 642 | 3 |
| 97 | GLM-5.3 Flash | 0.0000 | $5.38 | 133.7M | 325k | 9h 34m | 541 | 2 |
| 98 | Gemini 3.7 Flash | 0.0000 | $12.58 | 90.8M | 182k | 4h 36m | 317 | 1 |
| 99 | Kimi K3 | 0.0000 | $124.72 | 355.5M | 911k | 15h 41m | 948 | 24 |
| 100 | GLM-5.3 Flash | 0.0000 | $5.24 | 138.3M | 282k | 10h 25m | 542 | 3 |
| 101 | Qwen3.8-Max-0902 | 0.0000 | $29.45 | 86.5M | 1.2M | 20h 1m | 413 | 1 |
| 102 | Claude Fable 5 | 0.0000 | $175.12 | 145.0M | 372k | 12h 9m | 427 | 14 |
| 103 | Claude Sonnet 5.5 | 0.0000 | $140.54 | 573.5M | 2.0M | 18h 42m | 1322 | 5 |
| 104 | Claude Fable 5 | 0.0000 | $186.99 | 154.4M | 396k | 7h 35m | 429 | 9 |
| 105 | Muse Spark 1.3 | 0.0000 | $52.36 | 191.1M | 288k | 7h 43m | 680 | 5 |
| 106 | Muse Spark 1.3 | 0.0000 | $73.59 | 99.0M | 263k | 5h 24m | 459 | 3 |
| 107 | Claude Opus 5 | 0.0000 | $158.96 | 248.3M | 890k | 16h 5m | 693 | 15 |
| 108 | Claude Fable 5.1 | 0.0000 | $226.14 | 406.3M | 953k | 11h 14m | 902 | 15 |
| 109 | Gemini 3.7 Flash | 0.0000 | $6.58 | 51.9M | 91k | 1h 41m | 296 | 4 |
| 110 | Qwen3.8-Max-0902 | 0.0000 | $22.37 | 62.1M | 1.0M | 20h 3m | 330 | 1 |