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 | 0.1731 | $851.54 | 402.0M | 882k | 16h 28m | 928 | 15 |
| 2 | GPT-6 Astra | 0.1695 | $1429.90 | 682.5M | 1.4M | 13h 9m | 1631 | 15 |
| 3 | GPT-6 Astra | 0.1667 | $818.15 | 390.6M | 876k | 18h 17m | 988 | 21 |
| 4 | GPT-6 Astra | 0.1525 | $440.96 | 211.9M | 461k | 8h 1m | 546 | 7 |
| 5 | Gemini 4 Argon | 0.1524 | $41.91 | 58.1M | 431k | 9h 28m | 182 | 5 |
| 6 | GPT-6 Astra | 0.1519 | $408.97 | 200.1M | 427k | 5h 57m | 574 | 5 |
| 7 | Claude Sonnet 5.5 | 0.1449 | $60.59 | 259.5M | 700k | 17h 10m | 500 | 4 |
| 8 | Claude Opus 5.5 | 0.1412 | $32.15 | 111.5M | 374k | 16h 42m | 367 | 12 |
| 9 | Claude Opus 5 | 0.1388 | $55.40 | 79.2M | 435k | 18h 4m | 247 | 7 |
| 10 | Claude Opus 5.5 | 0.1378 | $36.38 | 124.0M | 438k | 17h 32m | 359 | 11 |
| 11 | Claude Sonnet 5.5 | 0.1364 | $65.26 | 259.5M | 1.1M | 17h 13m | 616 | 11 |
| 12 | Claude Opus 5 | 0.1349 | $50.16 | 72.9M | 377k | 16h 47m | 262 | 6 |
| 13 | GPT-5.6 Sol | 0.1316 | $55.65 | 69.9M | 170k | 12h 29m | 332 | 2 |
| 14 | GPT-5.6 Sol | 0.1312 | $87.71 | 101.7M | 199k | 15h 19m | 453 | 6 |
| 15 | Gemini 4 Argon | 0.1303 | $43.39 | 66.9M | 512k | 10h 28m | 195 | 7 |
| 16 | Claude Opus 5 | 0.1301 | $47.62 | 67.5M | 384k | 18h 51m | 247 | 5 |
| 17 | Claude Sonnet 5.5 | 0.1301 | $50.58 | 209.6M | 673k | 13h 41m | 408 | 10 |
| 18 | Gemini 4 Argon | 0.1252 | $72.74 | 47.3M | 391k | 5h 42m | 164 | 6 |
| 19 | Claude Haiku 5.5 | 0.1246 | $11.47 | 189.9M | 707k | 16h 52m | 400 | 6 |
| 20 | Claude Haiku 5.5 | 0.1232 | $6.74 | 107.0M | 520k | 13h 56m | 293 | 1 |
| 21 | Muse Spark 1.3 | 0.1200 | $62.04 | 57.0M | 274k | 16h 49m | 329 | 3 |
| 22 | Gemini 3.8 Flash | 0.1144 | $3.30 | 21.9M | 158k | 1h 16m | 160 | 5 |
| 23 | Claude Haiku 5.5 | 0.1135 | $6.58 | 101.1M | 551k | 18h 27m | 277 | 4 |
| 24 | Muse Spark 1.3 | 0.1131 | $41.90 | 45.4M | 252k | 18h 50m | 304 | 7 |
| 25 | Grok 4.7 | 0.1109 | $12.56 | 12.3M | 170k | 1h 49m | 85 | 2 |
| 26 | Kimi K3 | 0.1101 | $21.35 | 46.7M | 229k | 17h 35m | 282 | 6 |
| 27 | Grok 4.7 | 0.1098 | $130.86 | 121.5M | 481k | 15h 47m | 498 | 4 |
| 28 | Kimi K3 | 0.1097 | $26.90 | 62.8M | 258k | 19h 1m | 325 | 7 |
| 29 | Kimi K3 | 0.1091 | $18.21 | 39.5M | 209k | 19h 3m | 239 | 5 |
| 30 | Muse Spark 1.3 | 0.1082 | $55.03 | 49.7M | 225k | 19h 54m | 361 | 1 |
| 31 | Gemini 3.7 Flash | 0.1064 | $8.88 | 40.2M | 172k | 5h 7m | 265 | 2 |
| 32 | GLM-5.3 | 0.1050 | $34.13 | 75.8M | 305k | 18h 42m | 336 | 2 |
| 33 | Muse Spark 1.3 | 0.1039 | $52.80 | 46.7M | 249k | 19h 50m | 351 | 6 |
| 34 | GLM-5.3 | 0.1036 | $36.94 | 94.3M | 365k | 18h 38m | 359 | 3 |
| 35 | Gemini 3.8 Flash | 0.1027 | $5.15 | 41.3M | 171k | 2h 11m | 255 | 3 |
| 36 | Grok 4.6 | 0.1023 | $289.71 | 280.9M | 1.3M | 20h 0m | 1109 | 91 |
| 37 | Grok 4.7 | 0.0968 | $55.01 | 43.9M | 294k | 8h 31m | 190 | 6 |
| 38 | Qwen3.8-Max-0902 | 0.0947 | $60.29 | 210.7M | 1.0M | 19h 43m | 575 | 1 |
| 39 | GLM-5.3 | 0.0941 | $44.44 | 143.9M | 417k | 17h 20m | 450 | 8 |
| 40 | Grok 4.7 | 0.0896 | $57.29 | 42.5M | 256k | 5h 56m | 203 | 6 |
| 41 | Qwen3.8-Max | 0.0879 | $12.07 | 38.5M | 344k | 19h 44m | 290 | 3 |
| 42 | Gemini 3.7 Flash | 0.0865 | $5.25 | 20.8M | 119k | 3h 41m | 172 | 1 |
| 43 | Gemini 3.7 Flash | 0.0846 | $10.26 | 48.6M | 211k | 7h 0m | 264 | 3 |
| 44 | GLM-5.3 Flash | 0.0784 | $2.74 | 52.3M | 271k | 18h 56m | 251 | 2 |
| 45 | Grok 4.6 | 0.0709 | $86.33 | 77.3M | 437k | 10h 44m | 317 | 6 |
| 46 | Qwen3.8-Max | 0.0652 | $23.10 | 77.1M | 550k | 18h 46m | 436 | 2 |
| 47 | Muse Spark 1.2 | 0.0557 | $16.81 | 90.3M | 275k | 5h 28m | 342 | 4 |
| 48 | Muse Spark 1.2 | 0.0507 | $33.64 | 201.0M | 350k | 2h 20m | 488 | 3 |
| 49 | Claude Opus 5.5 | 0.0000 | $41.05 | 143.9M | 474k | 16h 43m | 419 | 14 |
| 50 | Inkling | 0.0000 | $4.78 | 4.9M | 42k | 32m | 136 | 1 |
| 51 | GLM-5.3 | 0.0000 | $28.55 | 71.5M | 295k | 19h 12m | 332 | 2 |
| 52 | Claude Sonnet 5.5 | 0.0000 | $60.75 | 240.5M | 1.0M | 19h 26m | 568 | 3 |
| 53 | Qwen3.8-Max-0902 | 0.0000 | $71.57 | 251.7M | 1.2M | 18h 34m | 626 | 3 |
| 54 | GLM-5.3 | 0.0000 | $43.34 | 125.4M | 382k | 18h 56m | 463 | 2 |
| 55 | Gemini 3.8 Flash | 0.0000 | $7.62 | 44.2M | 197k | 3h 25m | 241 | 4 |
| 56 | Claude Haiku 5.5 | 0.0000 | $7.52 | 117.0M | 598k | 11h 15m | 286 | 2 |
| 57 | GPT-5.6 Sol | 0.0000 | $29.44 | 43.7M | 172k | 11h 11m | 291 | 4 |
| 58 | Inkling | 0.0000 | $9.60 | 9.7M | 91k | 1h 37m | 187 | 1 |
| 59 | Grok 4.7 | 0.0000 | $47.01 | 35.3M | 253k | 6h 31m | 169 | 4 |
| 60 | Qwen3.8-Max | 0.0000 | $18.80 | 59.9M | 558k | 19h 4m | 366 | 1 |
| 61 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.89 | 103.3M | 298k | 19h 46m | 435 | 3 |
| 62 | DeepSeek V4 Flash Vision Exp | 0.0000 | $2.64 | 142.6M | 438k | 12h 9m | 474 | 5 |
| 63 | Claude Sonnet 5.5 | 0.0000 | $49.78 | 205.3M | 682k | 14h 7m | 417 | 8 |
| 64 | Inkling | 0.0000 | $4.22 | 4.3M | 40k | 1h 20m | 125 | 2 |
| 65 | GLM-5.3 Flash | 0.0000 | $5.34 | 102.1M | 341k | 17h 52m | 408 | 7 |
| 66 | Muse Spark 1.2 | 0.0000 | $8.11 | 42.2M | 266k | 2h 10m | 169 | 2 |
| 67 | Qwen3.8-Max | 0.0000 | $22.77 | 75.2M | 580k | 19h 13m | 492 | 3 |
| 68 | Qwen3.8-Max-0902 | 0.0000 | $64.31 | 226.9M | 1.0M | 19h 20m | 642 | 1 |
| 69 | GLM-5.3 Flash | 0.0000 | $2.82 | 72.3M | 274k | 18h 58m | 343 | 2 |
| 70 | Claude Haiku 5.5 | 0.0000 | $5.39 | 79.0M | 529k | 13h 40m | 215 | 3 |
| 71 | Grok 4.6 | 0.0000 | $51.24 | 39.8M | 426k | 15h 47m | 243 | 5 |
| 72 | Claude Opus 5.5 | 0.0000 | $25.87 | 82.9M | 352k | 17h 21m | 296 | 8 |
| 73 | GLM-5.3 Flash | 0.0000 | $2.38 | 59.1M | 248k | 15h 20m | 309 | 5 |
| 74 | Gemini 4 Argon | 0.0000 | $51.82 | 59.1M | 521k | 9h 41m | 178 | 5 |
| 75 | Gemini 3.8 Flash | 0.0000 | $7.44 | 46.3M | 203k | 3h 16m | 253 | 4 |
| 76 | Kimi K3 | 0.0000 | $18.66 | 38.3M | 209k | 20h 0m | 254 | 4 |
| 77 | DeepSeek V4 Flash Vision Exp | 0.0000 | $2.54 | 140.9M | 373k | 17h 33m | 473 | 5 |
| 78 | Qwen3.8-Max-0902 | 0.0000 | $63.28 | 220.8M | 1.1M | 19h 41m | 571 | 2 |
| 79 | Qwen3.8-Max | 0.0000 | $31.11 | 106.6M | 635k | 17h 29m | 500 | 3 |
| 80 | Inkling | 0.0000 | $9.21 | 9.4M | 67k | 2h 19m | 235 | 1 |
| 81 | GPT-5.6 Sol | 0.0000 | $115.28 | 137.3M | 233k | 11h 7m | 603 | 10 |
| 82 | Kimi K3 | 0.0000 | $31.98 | 77.8M | 334k | 19h 25m | 339 | 4 |
| 83 | GLM-5.3 Flash | 0.0000 | $2.95 | 54.2M | 261k | 17h 55m | 272 | 3 |
| 84 | Claude Opus 5 | 0.0000 | $35.03 | 47.7M | 304k | 18h 9m | 206 | 7 |
| 85 | Qwen3.8-Max-0902 | 0.0000 | $57.59 | 198.5M | 1.1M | 19h 22m | 561 | 3 |
| 86 | DeepSeek V4 Flash Vision Exp | 0.0000 | $2.76 | 151.1M | 447k | 15h 16m | 503 | 6 |
| 87 | GPT-5.6 Sol | 0.0000 | $33.43 | 41.9M | 177k | 7h 37m | 257 | 4 |
| 88 | Gemini 3.7 Flash | 0.0000 | $6.93 | 28.3M | 150k | 3h 32m | 203 | 4 |
| 89 | Grok 4.6 | 0.0000 | $192.75 | 185.2M | 1.2M | 14h 10m | 766 | 64 |
| 90 | Claude Opus 5 | 0.0000 | $44.13 | 62.7M | 352k | 17h 5m | 243 | 5 |
| 91 | DeepSeek V4 Flash Vision Exp | 0.0000 | $2.75 | 153.9M | 409k | 18h 4m | 510 | 2 |
| 92 | Muse Spark 1.3 | 0.0000 | $54.25 | 46.3M | 268k | 18h 59m | 310 | 2 |
| 93 | Grok 4.6 | 0.0000 | $86.81 | 76.6M | 468k | 16h 53m | 336 | 9 |
| 94 | Gemini 3.7 Flash | 0.0000 | $15.58 | 62.6M | 304k | 13h 22m | 285 | 2 |
| 95 | Gemini 4 Argon | 0.0000 | $75.16 | 54.4M | 420k | 6h 54m | 185 | 6 |
| 96 | Muse Spark 1.2 | 0.0000 | $7.49 | 39.5M | 207k | 4h 45m | 218 | 2 |
| 97 | Gemini 3.8 Flash | 0.0000 | $9.56 | 56.3M | 191k | 4h 7m | 303 | 3 |
| 98 | Muse Spark 1.2 | 0.0000 | $9.64 | 33.9M | 298k | 3h 46m | 194 | 5 |
| 99 | Inkling | 0.0000 | $6.19 | 6.3M | 42k | 29m | 120 | 1 |
| 100 | Claude Opus 5.5 | 0.0000 | $33.84 | 113.6M | 428k | 17h 31m | 346 | 9 |