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
1Muse Spark 1.20.0126$49.13229.2M341k8h 52m5756
2Muse Spark 1.20.0104$27.73109.9M451k7h 13m35810
3Muse Spark 1.20.0097$69.69161.5M457k8h 41m4415
4Muse Spark 1.20.0087$13.2553.2M190k6h 44m2953
5Muse Spark 1.20.0065$21.1865.3M269k5h 22m3133

Astronomy Toolkit

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.1013$11.0759.7M393k2h 7m2591
2Muse Spark 1.20.1000$12.1666.0M402k2h 34m2314
3Muse Spark 1.20.0563$26.3390.8M427k5h 8m2972
4Muse Spark 1.20.0000$53.10223.4M907k9h 16m5353
5Muse Spark 1.20.0000$11.0558.0M328k3h 11m2412

Cranelift Codegen Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$33.79127.0M205k10h 23m3565
2Muse Spark 1.20.0000$18.72115.3M194k3h 23m3504
3Muse Spark 1.20.0000$87.58303.3M711k10h 13m5625
4Muse Spark 1.20.0000$76.77223.4M655k10h 10m4507
5Muse Spark 1.20.0000$49.18242.6M532k8h 28m4959

Dart Style in Haskell

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.6241$2.2911.0M77k1h 6m1283
2Muse Spark 1.20.1043$2.539.5M123k1h 21m1011
3Muse Spark 1.20.1040$2.1810.0M104k1h 4m1132
4Muse Spark 1.20.1040$3.4116.0M109k59m1102
5Muse Spark 1.20.0377$5.5530.5M146k1h 16m1742

FFmpeg libswscale Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$15.4290.0M327k41m2862
2Muse Spark 1.20.0000$16.9785.6M384k1h 38m2274
3Muse Spark 1.20.0000$11.9064.7M340k1h 14m2232
4Muse Spark 1.20.0000$35.70203.8M978k3h 29m4688
5Muse Spark 1.20.0000$27.98159.1M568k1h 40m3452

Crash-Proof Flash Filesystem

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0049$36.55207.9M989k3h 16m45611
2Muse Spark 1.20.0047$53.94336.5M554k4h 31m6607
3Muse Spark 1.20.0038$13.6058.8M346k1h 50m1893
4Muse Spark 1.20.0033$35.75222.8M379k2h 39m4897
5Muse Spark 1.20.0000$18.5097.7M207k1h 10m2694

FrogsGame Post-Training

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0300$18.3645.0M166k4h 11m1765
2Muse Spark 1.20.0220$21.7448.9M286k5h 11m23911
3Muse Spark 1.20.0100$18.40105.2M433k4h 43m2515
4Muse Spark 1.20.0060$13.7365.6M312k5h 25m1839
5Muse Spark 1.20.0000$196.241245.9M587k4h 6m23898

Stepper Music Sequencer GBA

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0175$37.47155.3M1.3M5h 29m4607
2Muse Spark 1.20.0000$44.79140.1M936k4h 21m5434
3Muse Spark 1.20.0000$4.6818.3M123k58m1562
4Muse Spark 1.20.0000$53.1995.9M776k4h 50m3512
5Muse Spark 1.20.0000$10.5943.3M223k2h 38m2593

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

Git to Zig

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0185$42.33250.7M911k3h 1m5785
2Muse Spark 1.20.0000$2.459.3M123k59m862
3Muse Spark 1.20.0000$5.5326.0M135k1h 56m1754
4Muse Spark 1.20.0000$59.99358.3M658k4h 22m7791
5Muse Spark 1.20.0000$2.147.7M83k1h 10m933

† 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
1Muse Spark 1.20.8168$5.1625.8M238k1h 23m1693
2Muse Spark 1.20.7107$36.53207.7M800k2h 20m5271
3Muse Spark 1.20.0000$19.4092.0M1.0M4h 3m3073
4Muse Spark 1.20.0000$9.9353.1M354k2h 11m2586
5Muse Spark 1.20.0000$8.0539.0M223k1h 17m2014

Higgs Uncertainty Inference

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.9041$8.8738.4M436k2h 57m1501
2Muse Spark 1.20.7187$4.4015.5M216k1h 29m1102
3Muse Spark 1.20.7132$3.9618.1M225k49m1264
4Muse Spark 1.20.1494$13.1065.0M597k2h 52m2671
5Muse Spark 1.20.0498$2.478.0M164k1h 0m832

SGLang Inference System Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0532$132.47498.4M1.4M17h 13m14443
2Muse Spark 1.20.0099$100.58403.5M1.7M11h 46m11938
3Muse Spark 1.20.0081$15.0390.2M152k1h 36m2117
4Muse Spark 1.20.0047$67.55167.8M657k12h 12m5416
5Muse Spark 1.20.0000$32.8165.0M127k4h 50m2763

Lean 4 Kernel Type Checker in Pascal

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$19.14108.5M529k2h 29m3481
2Muse Spark 1.20.0000$21.0953.6M699k3h 48m2052
3Muse Spark 1.20.0000$29.46162.8M830k6h 1m4043
4Muse Spark 1.20.0000$27.3088.9M859k4h 46m2781
5Muse Spark 1.20.0000$9.5148.0M382k2h 35m2132

libexpat Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$40.00150.5M651k3h 23m3883
2Muse Spark 1.20.0000$41.66132.7M956k3h 49m4733
3Muse Spark 1.20.0000$16.5487.9M378k1h 23m3093
4Muse Spark 1.20.0000$39.83172.4M582k3h 18m5596
5Muse Spark 1.20.0000$32.92157.9M806k3h 52m3443

Lua Native Compiler

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$44.95118.1M616k6h 24m3542
2Muse Spark 1.20.0000$10.7739.0M388k1h 41m1644
3Muse Spark 1.20.0000$4.4622.6M149k52m1452
4Muse Spark 1.20.0000$22.61124.4M368k1h 49m3232
5Muse Spark 1.20.0000$12.0053.2M328k1h 52m1892

Machine-Learned Interatomic Potential

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.8888$4.0820.1M191k2h 11m16512
2Muse Spark 1.20.8642$31.30153.8M371k2h 47m46412
3Muse Spark 1.20.8223$3.4515.9M178k49m1273
4Muse Spark 1.20.7533$3.6517.8M164k1h 53m1263
5Muse Spark 1.20.7264$3.5517.0M170k2h 17m1443

Medium-Range Weather Forecast

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.3456$4.3818.4M145k37m1042
2Muse Spark 1.20.3227$38.37235.4M385k2h 26m5925
3Muse Spark 1.20.3018$11.6245.2M202k1h 9m1817
4Muse Spark 1.20.2944$2.128.7M99k50m861
5Muse Spark 1.20.2758$11.1751.5M378k2h 40m2116

MEG Speech Decoding

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.1659$17.1036.3M144k3h 7m1306
2Muse Spark 1.20.1175$9.5247.7M272k3h 44m1838
3Muse Spark 1.20.1011$11.9661.9M415k4h 37m2413
4Muse Spark 1.20.0000$13.1177.0M195k5h 0m2023
5Muse Spark 1.20.0000$16.3673.7M275k2h 42m2447

Wan 2.1 on MAX/Mojo

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0325$10.9349.7M405k2h 44m1823
2Muse Spark 1.20.0252$38.37181.5M771k3h 21m48113
3Muse Spark 1.20.0000$29.55111.8M325k3h 53m3312
4Muse Spark 1.20.0000$16.0877.6M385k3h 9m2542
5Muse Spark 1.20.0000$10.8049.7M240k3h 10m2263

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

MS/MS De Novo Generation

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0557$16.8190.3M275k5h 28m3424
2Muse Spark 1.20.0507$33.64201.0M350k2h 20m4883
3Muse Spark 1.20.0000$8.1142.2M266k2h 10m1692
4Muse Spark 1.20.0000$7.4939.5M207k4h 45m2182
5Muse Spark 1.20.0000$9.6433.9M298k3h 46m1945

Multi-GPU Efficient Finetuning

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.3810$64.94126.7M662k16h 40m38627
2Muse Spark 1.20.3095$11.9541.8M358k12h 44m19924
3Muse Spark 1.20.2619$355.312070.9M1.9M15h 46m592022
4Muse Spark 1.20.1905$5.5220.2M214k2h 15m1353
5Muse Spark 1.20.0476$35.64132.6M581k10h 53m45113

Notebook Compression

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.1646$89.68227.7M1.2M20h 2m7287
2Muse Spark 1.20.1353$32.24170.7M487k10h 37m5515
3Muse Spark 1.20.0816$32.40192.3M534k7h 46m5704
4Muse Spark 1.20.0387$183.05621.0M1.3M19h 7m14977
5Muse Spark 1.20.0356$37.95196.7M1.2M19h 2m6693

Flight-Sim Renderer in OpenGL

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$7.7740.8M287k2h 9m1825
2Muse Spark 1.20.0000$8.0738.9M412k3h 7m2024
3Muse Spark 1.20.0000$6.3024.2M135k1h 37m1594
4Muse Spark 1.20.0000$2.6412.4M42k2h 25m902
5Muse Spark 1.20.0000$1.728.1M39k1h 17m881

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

Optimizer Design

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$39.2585.0M351k13h 51m2757
2Muse Spark 1.20.0000$46.70116.8M475k9h 50m3648
3Muse Spark 1.20.0000$55.59163.2M672k19h 37m5671
4Muse Spark 1.20.0000$27.0448.5M345k6h 22m2563
5Muse Spark 1.20.0000$16.2119.8M148k19h 57m1881

PostgreSQL 18 on SQLite

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0055$37.82217.7M976k3h 48m49610
2Muse Spark 1.20.0055$40.72146.5M561k3h 14m4204
3Muse Spark 1.20.0000$32.40176.5M473k2h 53m4363
4Muse Spark 1.20.0000$14.0883.6M240k1h 8m3142
5Muse Spark 1.20.0000$33.19162.4M603k2h 4m4581

Quantum ESPRESSO pw.x in Rust

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0244$48.27287.1M1.0M3h 0m5981
2Muse Spark 1.20.0000$22.0858.0M685k1h 30m1943
3Muse Spark 1.20.0000$8.0039.5M393k1h 21m1662
4Muse Spark 1.20.0000$5.4530.5M131k29m1603
5Muse Spark 1.20.0000$10.3054.9M392k1h 20m2484

Qubit Routing

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.6114$9.2347.6M407k3h 16m2624
2Muse Spark 1.20.5947$9.3645.3M339k3h 54m2442
3Muse Spark 1.20.5914$9.2141.8M337k3h 53m2302
4Muse Spark 1.20.5787$10.6452.8M389k2h 30m2728
5Muse Spark 1.20.5545$7.7042.7M226k2h 46m2575

Reconnaissance Blind Chess Recovery

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.4036$5.4124.7M331k4h 44m1502
2Muse Spark 1.20.4036$6.7330.6M391k4h 23m1324
3Muse Spark 1.20.3750$11.1857.5M431k6h 54m2546
4Muse Spark 1.20.3429$9.0140.4M451k7h 47m1974
5Muse Spark 1.20.2071$9.6939.5M748k4h 22m1387

Fitness-Recap Video in Remotion

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0079$12.4662.2M180k3h 28m2703
2Muse Spark 1.20.0060$91.70184.1M1.3M8h 42m5093
3Muse Spark 1.20.0032$14.7129.2M224k3h 30m1832
4Muse Spark 1.20.0031$37.8575.3M303k4h 52m2854
5Muse Spark 1.20.0000$12.6638.1M209k4h 41m1901

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

Snooker Prediction

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$26.92100.5M603k1h 48m3775
2Muse Spark 1.20.0000$12.0849.7M275k1h 6m2508
3Muse Spark 1.20.0000$16.1178.5M517k1h 19m3094
4Muse Spark 1.20.0000$13.7075.9M319k1h 35m3053
5Muse Spark 1.20.0000$16.5887.1M508k2h 14m3216

SPICE Circuit Simulator in Rust

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.1313$32.05183.6M731k2h 8m4651
2Muse Spark 1.20.0707$10.8153.3M351k1h 35m2232
3Muse Spark 1.20.0707$32.82175.7M815k3h 21m4611
4Muse Spark 1.20.0505$8.7748.8M242k1h 16m1962
5Muse Spark 1.20.0404$5.3427.9M188k26m1432

Synthetic Music Diarization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.3829$88.55356.6M541k7h 12m7543
2Muse Spark 1.20.3711$10.8742.0M256k3h 30m2274
3Muse Spark 1.20.3611$12.5032.3M167k4h 4m2135
4Muse Spark 1.20.3544$13.5350.0M335k4h 26m2484
5Muse Spark 1.20.3434$13.4047.8M217k5h 21m2415

Vision-only TORCS Racing Bot

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0135$59.82110.7M431k11h 54m3316
2Muse Spark 1.20.0128$52.1470.4M490k14h 49m2894
3Muse Spark 1.20.0051$32.9057.9M354k9h 41m3723
4Muse Spark 1.20.0000$35.1065.9M265k9h 20m2293
5Muse Spark 1.20.0000$27.43124.8M316k10h 1m3854

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

Verilog Simulator in Swift

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0445$10.8558.8M321k1h 31m2292
2Muse Spark 1.20.0325$16.8184.3M312k1h 17m3292
3Muse Spark 1.20.0120$23.14130.5M679k1h 19m3953
4Muse Spark 1.20.0051$4.2721.5M175k51m1381
5Muse Spark 1.20.0000$10.6954.0M468k1h 50m2081