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 | GLM-5.3 | 0.8927 | $85.79 | 297.0M | 636k | 6h 7m | 634 | 7 |
| 2 | GLM-5.3 | 0.8719 | $51.39 | 174.8M | 618k | 4h 8m | 382 | 8 |
| 3 | DeepSeek V4 Flash Vision Exp | 0.8708 | $2.68 | 149.8M | 376k | 16h 23m | 473 | 5 |
| 4 | Claude Fable 5.1 | 0.8458 | $138.31 | 228.0M | 1000k | 9h 1m | 580 | 15 |
| 5 | GLM-5.3 | 0.8401 | $45.93 | 158.7M | 655k | 5h 28m | 343 | 6 |
| 6 | Claude Fable 5.1 | 0.8393 | $189.96 | 320.0M | 1.2M | 8h 30m | 718 | 28 |
| 7 | Claude Fable 5.1 | 0.8171 | $168.52 | 281.0M | 1.2M | 8h 8m | 667 | 16 |
| 8 | Muse Spark 1.2 | 0.8168 | $5.16 | 25.8M | 238k | 1h 23m | 169 | 3 |
| 9 | Qwen3.8-Max | 0.8086 | $63.86 | 200.9M | 2.1M | 18h 31m | 572 | 2 |
| 10 | Claude Fable 5.1 | 0.8047 | $204.26 | 349.5M | 1.2M | 8h 27m | 784 | 31 |
| 11 | Inkling | 0.7968 | $5.41 | 5.6M | 24k | 1h 10m | 98 | 3 |
| 12 | Inkling | 0.7910 | $2.64 | 2.7M | 12k | 47m | 61 | 2 |
| 13 | DeepSeek V4 Flash Vision Exp | 0.7876 | $3.53 | 195.8M | 540k | 19h 32m | 519 | 8 |
| 14 | Qwen3.8-Max | 0.7876 | $54.77 | 177.9M | 1.6M | 16h 1m | 520 | 5 |
| 15 | Kimi K3 | 0.7872 | $122.78 | 337.3M | 986k | 19h 10m | 771 | 36 |
| 16 | Claude Fable 5.1 | 0.7867 | $157.78 | 258.9M | 1.2M | 7h 40m | 582 | 11 |
| 17 | Gemini 3.7 Flash | 0.7839 | $8.97 | 84.4M | 442k | 56m | 281 | 3 |
| 18 | Kimi K3 | 0.7805 | $103.11 | 286.2M | 907k | 14h 49m | 651 | 10 |
| 19 | Inkling | 0.7670 | $5.68 | 5.8M | 36k | 1h 22m | 101 | 2 |
| 20 | GPT-5.6 | 0.7649 | $74.74 | 74.2M | 207k | 2h 36m | 270 | 5 |
| 21 | DeepSeek V4 Flash Vision Exp | 0.7578 | $8.78 | 501.2M | 1.2M | 13h 5m | 1157 | 3 |
| 22 | Kimi K3 | 0.7571 | $91.87 | 248.8M | 620k | 20h 0m | 531 | 50 |
| 23 | GLM-5.3 | 0.7528 | $38.94 | 126.7M | 486k | 4h 14m | 351 | 5 |
| 24 | Kimi K3 | 0.7477 | $74.48 | 205.5M | 639k | 8h 3m | 456 | 20 |
| 25 | DeepSeek V4 Flash Vision Exp | 0.7467 | $8.27 | 472.9M | 1.1M | 11h 58m | 1140 | 23 |
| 26 | GLM-5.3 | 0.7402 | $85.05 | 310.6M | 673k | 18h 16m | 645 | 8 |
| 27 | Grok 4.6 | 0.7305 | $58.74 | 52.8M | 626k | 4h 20m | 206 | 13 |
| 28 | Grok 4.6 | 0.7245 | $46.67 | 39.7M | 692k | 3h 57m | 169 | 10 |
| 29 | Qwen3.8-Max | 0.7188 | $63.39 | 207.4M | 1.7M | 17h 14m | 557 | 9 |
| 30 | Muse Spark 1.2 | 0.7107 | $36.53 | 207.7M | 800k | 2h 20m | 527 | 1 |
| 31 | Qwen3.8-Max | 0.7023 | $29.64 | 70.4M | 1.9M | 19h 40m | 330 | 1 |
| 32 | Qwen3.8-Max | 0.6658 | $53.16 | 162.1M | 1.8M | 18h 29m | 495 | 2 |
| 33 | Grok 4.6 | 0.6586 | $55.70 | 47.5M | 700k | 4h 6m | 194 | 10 |
| 34 | Grok 4.6 | 0.6473 | $57.88 | 51.1M | 725k | 4h 13m | 210 | 5 |
| 35 | GPT-5.6 | 0.6303 | $111.93 | 116.6M | 261k | 11h 2m | 425 | 3 |
| 36 | Kimi K3 | 0.6169 | $112.73 | 307.9M | 980k | 13h 16m | 708 | 31 |
| 37 | GPT-5.6 | 0.6093 | $23.53 | 32.7M | 162k | 1h 28m | 207 | 3 |
| 38 | DeepSeek V4 Flash Vision Exp | 0.4680 | $3.00 | 159.1M | 520k | 6h 30m | 442 | 5 |
| 39 | GPT-5.6 | 0.4658 | $119.15 | 122.5M | 308k | 3h 17m | 463 | 6 |
| 40 | Gemini 3.7 Flash | 0.3912 | $15.89 | 144.8M | 798k | 2h 17m | 479 | 5 |
| 41 | GPT-5.6 | 0.3383 | $180.46 | 175.3M | 266k | 4h 7m | 474 | 10 |
| 42 | Gemini 3.7 Flash | 0.3149 | $10.74 | 97.9M | 514k | 1h 12m | 278 | 2 |
| 43 | Grok 4.6 | 0.2777 | $27.64 | 23.0M | 551k | 3h 18m | 127 | 2 |
| 44 | Gemini 3.7 Flash | 0.2425 | $12.51 | 121.4M | 559k | 2h 10m | 326 | 2 |
| 45 | Gemini 3.7 Flash | 0.2101 | $6.70 | 49.8M | 379k | 47m | 212 | 3 |
| 46 | Inkling | 0.0000 | $7.50 | 7.7M | 51k | 1h 46m | 135 | 1 |
| 47 | Muse Spark 1.2 | 0.0000 | $19.40 | 92.0M | 1.0M | 4h 3m | 307 | 3 |
| 48 | Muse Spark 1.2 | 0.0000 | $9.93 | 53.1M | 354k | 2h 11m | 258 | 6 |
| 49 | Muse Spark 1.2 | 0.0000 | $8.05 | 39.0M | 223k | 1h 17m | 201 | 4 |
| 50 | Inkling | 0.0000 | $4.66 | 4.8M | 18k | 1h 13m | 91 | 2 |