Traces

Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.

Kolmogorov Audio Compression

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0240$13.44120.0M296k7h 42m4657
2Gemini 3.7 Flash0.0232$21.26112.5M588k9h 45m34020
3Gemini 3.7 Flash0.0189$26.8583.8M686k9h 43m26716
4Gemini 3.7 Flash0.0110$6.6319.2M229k5h 4m1665
5Gemini 3.7 Flash0.0097$3.4713.3M97k5h 22m1534

Astronomy Toolkit

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.7294$8.3949.1M408k2h 12m2181
2Gemini 3.7 Flash0.4014$3.0923.0M225k38m1533
3Gemini 3.7 Flash0.0000$5.4438.0M299k1h 47m1973
4Gemini 3.7 Flash0.0000$3.9124.5M212k1h 28m1552
5Gemini 3.7 Flash0.0000$3.8223.6M220k46m1622

Cranelift Codegen Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0802$35.86231.6M242k6h 15m57420
2Gemini 3.7 Flash0.0189$20.57157.5M204k2h 49m43217
3Gemini 3.7 Flash0.0110$23.00164.8M188k4h 11m49519
4Gemini 3.7 Flash0.0000$30.61210.1M211k5h 15m59321
5Gemini 3.7 Flash0.0000$47.46341.2M378k8h 44m82822

Dart Style in Haskell

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.6517$199.282123.1M2.6M19h 55m491762
2Gemini 3.7 Flash0.5376$121.241110.9M1.5M19h 27m252437
3Gemini 3.7 Flash0.4365$75.56629.3M934k19h 55m13313
4Gemini 3.7 Flash0.4242$33.92324.0M891k3h 25m7808
5Gemini 3.7 Flash0.3137$25.24282.5M578k1h 28m5902

FFmpeg libswscale Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0125$20.83184.0M617k2h 35m5242
2Gemini 3.7 Flash0.0032$19.94167.8M795k2h 4m4967
3Gemini 3.7 Flash0.0000$25.27228.2M1.1M2h 14m6555
4Gemini 3.7 Flash0.0000$16.99131.7M937k2h 45m4486
5Gemini 3.7 Flash0.0000$44.74251.9M922k8h 1m7586

Crash-Proof Flash Filesystem

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0217$93.80813.5M2.3M19h 56m21411
2Gemini 3.7 Flash0.0112$89.95756.9M1.7M20h 0m19071
3Gemini 3.7 Flash0.0049$62.15472.1M1.5M20h 0m11391
4Gemini 3.7 Flash0.0024$124.701220.5M2.9M20h 0m27951
5Gemini 3.7 Flash0.0010$64.73520.0M1.4M20h 0m13561

FrogsGame Post-Training

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0620$5.0314.3M76k5h 27m1281
2Gemini 3.7 Flash0.0420$30.7272.9M130k16h 34m3011
3Gemini 3.7 Flash0.0320$45.33138.6M173k19h 58m3961
4Gemini 3.7 Flash0.0220$3.8024.6M101k2h 41m1422
5Gemini 3.7 Flash0.0200$37.0796.2M140k17h 26m3211

Stepper Music Sequencer GBA

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.2415$49.29499.9M1.0M4h 48m13022
2Gemini 3.7 Flash0.1895$40.63436.9M982k3h 1m11342
3Gemini 3.7 Flash0.1724$88.83943.5M2.1M6h 27m24491
4Gemini 3.7 Flash0.1698$29.14318.3M646k2h 19m8562
5Gemini 3.7 Flash0.1224$55.17592.3M1.3M5h 23m15075

Git to Zig

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1808$157.011517.8M2.4M19h 43m32561
2Gemini 3.7 Flash0.1495$79.59838.0M1.2M20h 0m18552
3Gemini 3.7 Flash0.1433$101.571069.8M1.5M19h 58m23721
4Gemini 3.7 Flash0.1237$71.55746.3M1.3M19h 57m16904
5Gemini 3.7 Flash0.0000$76.41819.6M1.5M19h 43m17341

† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.

Granite Mamba2 Inference Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.7839$8.9784.4M442k56m2813
2Gemini 3.7 Flash0.3912$15.89144.8M798k2h 17m4795
3Gemini 3.7 Flash0.3149$10.7497.9M514k1h 12m2782
4Gemini 3.7 Flash0.2425$12.51121.4M559k2h 10m3262
5Gemini 3.7 Flash0.2101$6.7049.8M379k47m2123

Higgs Uncertainty Inference

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1681$1.729.3M135k1h 3m1021
2Gemini 3.7 Flash0.1295$1.9810.2M141k50m1053
3Gemini 3.7 Flash0.1075$1.629.2M146k1h 7m1021
4Gemini 3.7 Flash0.0798$2.5310.3M161k1h 26m1101
5Gemini 3.7 Flash0.0647$3.7920.7M194k1h 41m1392

SGLang Inference System Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0169$19.15195.9M289k3h 33m5054
2Gemini 3.7 Flash0.0000$9.47100.2M149k1h 43m3164
3Gemini 3.7 Flash0.0000$9.0285.7M143k1h 52m3061
4Gemini 3.7 Flash0.0000$12.5890.8M182k4h 36m3171
5Gemini 3.7 Flash0.0000$6.5851.9M91k1h 41m2964

Lean 4 Kernel Type Checker in Pascal

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.9448$95.08678.0M1.4M19h 49m16601
2Gemini 3.7 Flash0.9361$54.83453.2M1.3M12h 43m12241
3Gemini 3.7 Flash0.1248$74.81557.5M1.1M14h 22m12171
4Gemini 3.7 Flash0.0087$48.94384.1M939k13h 20m11181
5Gemini 3.7 Flash0.0000$101.50861.0M1.8M19h 58m20921

libexpat Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.2399$41.35394.7M960k4h 30m10096
2Gemini 3.7 Flash0.1572$41.30358.7M785k6h 1m8995
3Gemini 3.7 Flash0.1555$24.69216.5M877k2h 56m6242
4Gemini 3.7 Flash0.0000$33.92328.7M960k2h 58m81020
5Gemini 3.7 Flash0.0000$29.56325.1M599k2h 10m8302

Lua Native Compiler

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.6998$21.69183.4M580k2h 58m4001
2Gemini 3.7 Flash0.6541$62.39519.3M1.2M7h 8m12601
3Gemini 3.7 Flash0.6517$26.08255.3M824k1h 58m6701
4Gemini 3.7 Flash0.6392$29.13278.2M822k3h 5m7511
5Gemini 3.7 Flash0.3270$79.34743.6M1.7M8h 42m18151

Machine-Learned Interatomic Potential

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.8422$11.4530.2M159k8h 5m2083
2Gemini 3.7 Flash0.7285$10.9529.5M154k8h 16m2137
3Gemini 3.7 Flash0.5113$8.2127.8M178k5h 29m1842
4Gemini 3.7 Flash0.4203$5.2521.8M116k4h 45m1781
5Gemini 3.7 Flash0.0010$6.0120.4M174k4h 35m1542

Medium-Range Weather Forecast

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.5747$22.4049.9M145k13h 34m2567
2Gemini 3.7 Flash0.5566$16.5654.7M160k9h 58m2852
3Gemini 3.7 Flash0.5365$13.1137.7M147k6h 21m2413
4Gemini 3.7 Flash0.5356$19.3648.1M172k8h 5m2524
5Gemini 3.7 Flash0.5332$4.9921.4M136k4h 20m1711

MEG Speech Decoding

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1130$4.8733.1M132k3h 51m2261
2Gemini 3.7 Flash0.1121$12.1251.3M122k7h 24m3124
3Gemini 3.7 Flash0.0948$9.9338.7M111k7h 46m2665
4Gemini 3.7 Flash0.0854$10.1135.8M110k7h 53m3031
5Gemini 3.7 Flash0.0000$12.2048.7M173k7h 50m2852

Wan 2.1 on MAX/Mojo

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0349$23.63178.6M776k6h 26m5691
2Gemini 3.7 Flash0.0347$27.48166.6M453k6h 47m4381
3Gemini 3.7 Flash0.0331$42.63248.9M797k11h 49m7161
4Gemini 3.7 Flash0.0317$28.92149.4M462k8h 34m3801
5Gemini 3.7 Flash0.0310$36.97183.1M560k8h 49m4831

MS/MS De Novo Generation

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1064$8.8840.2M172k5h 7m2652
2Gemini 3.7 Flash0.0865$5.2520.8M119k3h 41m1721
3Gemini 3.7 Flash0.0846$10.2648.6M211k7h 0m2643
4Gemini 3.7 Flash0.0000$6.9328.3M150k3h 32m2034
5Gemini 3.7 Flash0.0000$15.5862.6M304k13h 22m2852

Multi-GPU Efficient Finetuning

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.2143$10.2429.6M72k9h 49m18131
2Gemini 3.7 Flash0.1667$11.8531.1M102k19h 53m20210
3Gemini 3.7 Flash0.0000$22.1847.8M107k18h 31m2992
4Gemini 3.7 Flash0.0000$8.3027.1M102k9h 38m18810
5Gemini 3.7 Flash0.0000$30.3173.0M132k18h 49m31013

Notebook Compression

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1775$2.9513.6M108k3h 17m1292
2Gemini 3.7 Flash0.1714$6.9227.7M160k6h 28m2365
3Gemini 3.7 Flash0.0417$2.9916.0M112k3h 8m1656
4Gemini 3.7 Flash0.0412$3.0519.8M150k3h 10m19410
5Gemini 3.7 Flash0.0403$4.5617.9M128k4h 20m1458

Flight-Sim Renderer in OpenGL

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0116$11.2868.7M237k4h 7m3042
2Gemini 3.7 Flash0.0064$35.75195.3M360k8h 28m5551
3Gemini 3.7 Flash0.0054$6.5251.3M224k2h 40m2742
4Gemini 3.7 Flash0.0020$17.05105.9M300k5h 32m3811
5Gemini 3.7 Flash0.0009$11.2877.4M230k5h 1m3693

Optimizer Design

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1194$22.13241.0M134k10h 36m8342
2Gemini 3.7 Flash0.0537$10.3785.1M122k13h 22m4352
3Gemini 3.7 Flash0.0405$25.34217.9M182k10h 29m7442
4Gemini 3.7 Flash0.0000$28.88259.5M185k18h 35m9081
5Gemini 3.7 Flash0.0000$12.4147.0M144k13h 48m2972

PostgreSQL 18 on SQLite

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.2582$124.971333.8M2.5M11h 51m301437
2Gemini 3.7 Flash0.2418$144.251592.6M2.6M19h 46m345039
3Gemini 3.7 Flash0.2253$193.892112.9M3.0M19h 55m468016
4Gemini 3.7 Flash0.1758$159.991689.8M2.8M19h 49m375113
5Gemini 3.7 Flash0.0495$17.96182.1M620k1h 34m4022

Quantum ESPRESSO pw.x in Rust

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.1545$46.71314.3M747k10h 28m7402
2Gemini 3.7 Flash0.0976$71.79423.8M777k17h 50m9483
3Gemini 3.7 Flash0.0650$36.49288.8M712k6h 10m7252
4Gemini 3.7 Flash0.0000$51.00393.0M804k11h 3m10024
5Gemini 3.7 Flash0.0000$24.96238.1M690k3h 15m5392

Qubit Routing

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.7591$2.339.2M139k1h 43m992
2Gemini 3.7 Flash0.6672$3.0415.3M126k1h 37m1401
3Gemini 3.7 Flash0.6446$3.4416.9M214k2h 28m1512
4Gemini 3.7 Flash0.6074$16.2672.9M429k6h 43m2805
5Gemini 3.7 Flash0.5912$5.6344.5M188k5h 26m2701

Reconnaissance Blind Chess Recovery

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.4250$12.0951.0M293k4h 11m2663
2Gemini 3.7 Flash0.3000$23.11214.3M578k5h 22m5241
3Gemini 3.7 Flash0.2393$20.54111.4M562k4h 43m3271
4Gemini 3.7 Flash0.0536$30.51186.7M1.3M5h 45m5132
5Gemini 3.7 Flash0.0429$30.88192.0M568k8h 45m5062

Fitness-Recap Video in Remotion

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0129$13.97114.7M211k4h 23m3822
2Gemini 3.7 Flash0.0091$2.9421.2M86k1h 20m1692
3Gemini 3.7 Flash0.0089$10.4467.7M164k2h 48m3284
4Gemini 3.7 Flash0.0080$7.6861.7M148k2h 7m3001
5Gemini 3.7 Flash0.0060$4.6730.1M112k2h 7m2221

Snooker Prediction

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0000$7.8266.5M374k1h 5m2791
2Gemini 3.7 Flash0.0000$8.3359.1M343k2h 40m2823
3Gemini 3.7 Flash0.0000$5.6140.2M288k59m2242
4Gemini 3.7 Flash0.0000$6.6448.6M323k1h 55m2471
5Gemini 3.7 Flash0.0000$7.4056.9M413k1h 21m2662

SPICE Circuit Simulator in Rust

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.6263$99.311037.7M2.0M6h 16m25774
2Gemini 3.7 Flash0.5253$121.421230.5M2.0M12h 5m29493
3Gemini 3.7 Flash0.4747$76.85790.2M1.6M4h 46m20172
4Gemini 3.7 Flash0.4444$80.51766.1M1.3M6h 23m17937
5Gemini 3.7 Flash0.3737$126.281246.3M2.0M12h 6m29212

Synthetic Music Diarization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.4776$32.86129.1M265k12h 34m4382
2Gemini 3.7 Flash0.4664$11.2742.4M155k7h 29m2542
3Gemini 3.7 Flash0.4422$14.36133.2M250k5h 49m3892
4Gemini 3.7 Flash0.4264$42.51256.4M394k13h 10m6819
5Gemini 3.7 Flash0.4000$15.6783.4M201k4h 25m3221

Vision-only TORCS Racing Bot

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.0235$5.0624.8M145k2h 40m1971
2Gemini 3.7 Flash0.0127$18.6692.0M417k5h 34m3182
3Gemini 3.7 Flash0.0121$11.5163.9M262k4h 49m3102
4Gemini 3.7 Flash0.0118$6.8126.5M177k3h 38m1832
5Gemini 3.7 Flash0.0041$7.3932.0M185k3h 17m2131

Verilog Simulator in Swift

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 3.7 Flash0.8305$103.651018.6M2.0M19h 58m24181
2Gemini 3.7 Flash0.8288$74.39745.3M2.1M17h 44m18281
3Gemini 3.7 Flash0.8202$75.29725.4M1.4M19h 4m16512
4Gemini 3.7 Flash0.5976$41.43380.1M776k20h 1m9444
5Gemini 3.7 Flash0.3545$53.22180.3M689k19h 59m5741