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 | Claude Sonnet 5.5 | 0.3980 | $50.51 | 215.5M | 568k | 17h 35m | 475 | 11 |
| 2 | GPT-6 Astra | 0.3919 | $899.22 | 430.4M | 993k | 17h 31m | 1064 | 15 |
| 3 | Gemini 4 Argon | 0.3815 | $127.65 | 83.3M | 493k | 10h 58m | 219 | 7 |
| 4 | GPT-6 Astra | 0.3729 | $274.60 | 132.9M | 344k | 8h 16m | 411 | 13 |
| 5 | Claude Opus 5.5 | 0.3727 | $24.06 | 81.6M | 282k | 17h 26m | 303 | 14 |
| 6 | GPT-6 Astra | 0.3704 | $154.28 | 76.5M | 270k | 4h 15m | 297 | 9 |
| 7 | Claude Opus 5.5 | 0.3678 | $32.59 | 115.1M | 354k | 17h 32m | 353 | 13 |
| 8 | Claude Opus 5.5 | 0.3676 | $34.48 | 123.3M | 365k | 14h 56m | 393 | 16 |
| 9 | Muse Spark 1.3 | 0.3657 | $29.63 | 28.5M | 123k | 19h 14m | 290 | 12 |
| 10 | Claude Haiku 5.5 | 0.3592 | $3.57 | 53.4M | 356k | 17h 25m | 205 | 1 |
| 11 | Claude Opus 5 | 0.3591 | $41.25 | 57.4M | 336k | 16h 38m | 244 | 11 |
| 12 | Claude Haiku 5.5 | 0.3589 | $6.16 | 99.7M | 434k | 15h 47m | 312 | 1 |
| 13 | GPT-6 Astra | 0.3557 | $452.78 | 217.0M | 444k | 15h 46m | 527 | 14 |
| 14 | Gemini 4 Argon | 0.3541 | $66.65 | 65.7M | 370k | 10h 16m | 208 | 6 |
| 15 | Gemini 4 Argon | 0.3496 | $73.61 | 73.2M | 523k | 11h 46m | 215 | 9 |
| 16 | GPT-6 Astra | 0.3431 | $526.36 | 253.0M | 673k | 17h 55m | 694 | 20 |
| 17 | Claude Sonnet 5.5 | 0.3387 | $39.17 | 161.4M | 527k | 11h 58m | 374 | 2 |
| 18 | Claude Sonnet 5.5 | 0.3362 | $42.30 | 176.9M | 528k | 15h 36m | 407 | 2 |
| 19 | Claude Sonnet 5.5 | 0.3295 | $44.28 | 184.1M | 576k | 15h 25m | 433 | 1 |
| 20 | Gemini 4 Argon | 0.3253 | $89.40 | 63.7M | 382k | 14h 54m | 195 | 7 |
| 21 | Claude Haiku 5.5 | 0.3229 | $5.52 | 86.2M | 451k | 9h 19m | 265 | 3 |
| 22 | Claude Opus 5 | 0.3182 | $39.66 | 57.3M | 295k | 17h 37m | 258 | 3 |
| 23 | Claude Fable 5.1 | 0.3166 | $19.44 | 30.2M | 179k | 16h 28m | 214 | 8 |
| 24 | Claude Fable 5.1 | 0.3123 | $26.35 | 42.8M | 204k | 16h 51m | 240 | 12 |
| 25 | GPT-5.6 Sol | 0.3119 | $41.21 | 43.5M | 133k | 5h 23m | 204 | 2 |
| 26 | Claude Fable 5.1 | 0.3116 | $13.99 | 21.5M | 133k | 17h 11m | 192 | 11 |
| 27 | Claude Sonnet 5.5 | 0.3091 | $43.33 | 180.7M | 552k | 16h 17m | 436 | 14 |
| 28 | Claude Fable 5.1 | 0.3057 | $16.57 | 26.2M | 144k | 13h 23m | 202 | 11 |
| 29 | Grok 4.6 | 0.3041 | $128.46 | 122.4M | 984k | 15h 5m | 545 | 23 |
| 30 | GPT-5.6 Sol | 0.3039 | $14.10 | 19.5M | 85k | 2h 25m | 137 | 2 |
| 31 | Claude Opus 5 | 0.3001 | $47.82 | 68.3M | 371k | 18h 4m | 251 | 14 |
| 32 | Claude Opus 5.5 | 0.2944 | $25.47 | 87.0M | 298k | 19h 1m | 298 | 14 |
| 33 | Claude Fable 5 | 0.2869 | $40.93 | 27.8M | 172k | 18h 49m | 197 | 7 |
| 34 | Claude Fable 5 | 0.2738 | $32.57 | 21.0M | 153k | 17h 28m | 176 | 7 |
| 35 | Claude Haiku 5.5 | 0.2649 | $5.00 | 78.8M | 385k | 13h 42m | 250 | 1 |
| 36 | Claude Haiku 5.5 | 0.2545 | $5.81 | 88.4M | 483k | 16h 59m | 251 | 6 |
| 37 | Claude Fable 5 | 0.2462 | $69.13 | 51.5M | 236k | 18h 13m | 278 | 10 |
| 38 | GPT-5.6 Sol | 0.2311 | $153.75 | 128.1M | 180k | 10h 45m | 298 | 17 |
| 39 | Grok 4.6 | 0.2265 | $217.69 | 204.9M | 1.2M | 19h 25m | 878 | 23 |
| 40 | GLM-5.3 | 0.2244 | $22.68 | 51.0M | 188k | 18h 6m | 315 | 2 |
| 41 | Claude Fable 5.1 | 0.2155 | $25.98 | 41.7M | 212k | 14h 56m | 237 | 10 |
| 42 | Grok 4.6 | 0.2107 | $132.86 | 129.3M | 708k | 19h 25m | 571 | 33 |
| 43 | GLM-5.3 | 0.2036 | $34.96 | 74.2M | 244k | 14h 55m | 372 | 2 |
| 44 | GLM-5.3 Flash | 0.2035 | $2.39 | 39.2M | 192k | 18h 35m | 253 | 3 |
| 45 | Gemini 4 Argon | 0.1941 | $62.22 | 52.9M | 318k | 10h 43m | 182 | 5 |
| 46 | Claude Opus 5.5 | 0.1928 | $24.23 | 78.6M | 314k | 16h 53m | 281 | 9 |
| 47 | GPT-5.6 Sol | 0.1902 | $64.35 | 67.7M | 163k | 7h 2m | 279 | 4 |
| 48 | Qwen3.8-Max-0902 | 0.1889 | $35.75 | 119.7M | 797k | 19h 10m | 470 | 2 |
| 49 | Qwen3.8-Max-0902 | 0.1871 | $50.73 | 177.9M | 853k | 19h 26m | 592 | 1 |
| 50 | GPT-5.6 Sol | 0.1862 | $104.80 | 98.3M | 165k | 7h 53m | 318 | 8 |
| 51 | Grok 4.6 | 0.1844 | $95.16 | 83.3M | 284k | 18h 58m | 362 | 11 |
| 52 | DeepSeek V4 Flash Vision Exp | 0.1749 | $1.32 | 68.7M | 240k | 18h 36m | 359 | 6 |
| 53 | Grok 4.7 | 0.1697 | $27.46 | 25.8M | 199k | 3h 25m | 133 | 5 |
| 54 | Muse Spark 1.2 | 0.1659 | $17.10 | 36.3M | 144k | 3h 7m | 130 | 6 |
| 55 | GLM-5.3 | 0.1492 | $27.34 | 90.5M | 318k | 15h 42m | 371 | 3 |
| 56 | Qwen3.8-Max | 0.1460 | $13.18 | 43.8M | 302k | 19h 37m | 333 | 7 |
| 57 | Muse Spark 1.3 | 0.1430 | $33.98 | 30.2M | 124k | 18h 44m | 278 | 4 |
| 58 | Claude Fable 5 | 0.1418 | $35.13 | 22.9M | 161k | 18h 17m | 176 | 7 |
| 59 | GLM-5.3 Flash | 0.1356 | $1.97 | 44.0M | 221k | 9h 31m | 277 | 4 |
| 60 | Muse Spark 1.3 | 0.1334 | $8.50 | 30.2M | 106k | 18h 10m | 317 | 7 |
| 61 | Claude Opus 5 | 0.1306 | $32.65 | 45.8M | 261k | 17h 4m | 232 | 9 |
| 62 | Claude Fable 5 | 0.1281 | $60.54 | 43.7M | 223k | 17h 15m | 249 | 11 |
| 63 | Qwen3.8-Max-0902 | 0.1258 | $56.59 | 193.9M | 1.1M | 18h 55m | 561 | 4 |
| 64 | Grok 4.6 | 0.1245 | $71.38 | 67.2M | 365k | 9h 53m | 293 | 10 |
| 65 | GLM-5.3 Flash | 0.1202 | $2.02 | 38.5M | 189k | 18h 41m | 272 | 4 |
| 66 | Muse Spark 1.3 | 0.1187 | $59.14 | 56.9M | 180k | 14h 50m | 367 | 3 |
| 67 | Muse Spark 1.2 | 0.1175 | $9.52 | 47.7M | 272k | 3h 44m | 183 | 8 |
| 68 | Gemini 3.7 Flash | 0.1130 | $4.87 | 33.1M | 132k | 3h 51m | 226 | 1 |
| 69 | Gemini 3.7 Flash | 0.1121 | $12.12 | 51.3M | 122k | 7h 24m | 312 | 4 |
| 70 | Kimi K3 | 0.1102 | $14.90 | 32.2M | 173k | 18h 22m | 254 | 3 |
| 71 | GLM-5.3 Flash | 0.1039 | $3.76 | 97.3M | 271k | 17h 33m | 431 | 2 |
| 72 | GLM-5.3 | 0.1032 | $33.80 | 77.7M | 262k | 19h 7m | 353 | 2 |
| 73 | Gemini 3.8 Flash | 0.1012 | $4.22 | 32.1M | 134k | 3h 25m | 220 | 3 |
| 74 | Muse Spark 1.2 | 0.1011 | $11.96 | 61.9M | 415k | 4h 37m | 241 | 3 |
| 75 | Qwen3.8-Max | 0.0985 | $20.47 | 70.2M | 412k | 18h 53m | 478 | 2 |
| 76 | Gemini 3.8 Flash | 0.0958 | $3.90 | 29.7M | 119k | 2h 37m | 202 | 3 |
| 77 | Gemini 3.7 Flash | 0.0948 | $9.93 | 38.7M | 111k | 7h 46m | 266 | 5 |
| 78 | Qwen3.8-Max-0902 | 0.0904 | $20.15 | 52.8M | 623k | 19h 46m | 279 | 2 |
| 79 | Gemini 3.7 Flash | 0.0854 | $10.11 | 35.8M | 110k | 7h 53m | 303 | 1 |
| 80 | DeepSeek V4 Flash Vision Exp | 0.0826 | $1.73 | 93.5M | 273k | 12h 25m | 457 | 2 |
| 81 | Gemini 3.8 Flash | 0.0714 | $6.78 | 37.1M | 131k | 5h 53m | 235 | 4 |
| 82 | GLM-5.3 | 0.0000 | $49.90 | 134.3M | 340k | 19h 4m | 469 | 21 |
| 83 | GLM-5.3 Flash | 0.0000 | $1.17 | 35.7M | 150k | 19h 11m | 277 | 4 |
| 84 | Muse Spark 1.3 | 0.0000 | $32.86 | 29.1M | 146k | 18h 59m | 269 | 6 |
| 85 | Qwen3.8-Max | 0.0000 | $13.84 | 45.7M | 331k | 19h 21m | 336 | 2 |
| 86 | Inkling | 0.0000 | $5.29 | 5.5M | 26k | 1h 28m | 151 | 1 |
| 87 | Grok 4.7 | 0.0000 | $17.01 | 16.9M | 171k | 3h 5m | 110 | 2 |
| 88 | Grok 4.7 | 0.0000 | $33.74 | 29.5M | 210k | 5h 34m | 157 | 5 |
| 89 | Qwen3.8-Max | 0.0000 | $27.96 | 99.7M | 412k | 19h 32m | 527 | 4 |
| 90 | Muse Spark 1.2 | 0.0000 | $13.11 | 77.0M | 195k | 5h 0m | 202 | 3 |
| 91 | Inkling | 0.0000 | $5.01 | 5.2M | 28k | 1h 29m | 128 | 1 |
| 92 | Qwen3.8-Max-0902 | 0.0000 | $24.18 | 67.0M | 860k | 20h 1m | 341 | 1 |
| 93 | Gemini 3.7 Flash | 0.0000 | $12.20 | 48.7M | 173k | 7h 50m | 285 | 2 |
| 94 | Grok 4.7 | 0.0000 | $9.82 | 11.5M | 148k | 1h 49m | 85 | 2 |
| 95 | Muse Spark 1.2 | 0.0000 | $16.36 | 73.7M | 275k | 2h 42m | 244 | 7 |
| 96 | Gemini 3.8 Flash | 0.0000 | $6.01 | 39.8M | 130k | 3h 31m | 254 | 7 |
| 97 | Inkling | 0.0000 | $6.23 | 6.3M | 53k | 2h 6m | 139 | 1 |
| 98 | Gemini 3.8 Flash | 0.0000 | $6.66 | 41.6M | 150k | 3h 57m | 251 | 6 |
| 99 | Qwen3.8-Max | 0.0000 | $8.55 | 26.2M | 281k | 19h 56m | 242 | 1 |
| 100 | Grok 4.7 | 0.0000 | $32.99 | 32.5M | 199k | 5h 31m | 181 | 4 |
| 101 | Inkling | 0.0000 | $5.31 | 5.5M | 23k | 2h 3m | 134 | 2 |
| 102 | Claude Opus 5 | 0.0000 | $41.18 | 59.8M | 304k | 17h 59m | 267 | 9 |
| 103 | Inkling | 0.0000 | $5.42 | 5.6M | 24k | 1h 30m | 116 | 1 |