Welcome to the comma.ai leaderboard! We designed these challenges around real problems we've faced while building and shipping openpilot. We hope you enjoy them. If you do and score well, you'll probably enjoy a job here. * Submit your solution here * Multiple submissions are allowed * Non-competitive scores will not be published * is an employee or intern score * Active challenges are still expected to be difficult * Archived challenges are (mostly) solved problems
Score = PCBA bounding box volume (mm³) + 50 × number of vias + 5,000 × number of copper layers. Lowest score wins.
$1,000 cash prize for the lowest score by October 12, 2026.
👑 challenge prize winner
💡 new approach
📖 best write-up
| score | name | link | |
|---|---|---|---|
| 0.162 | semantic-pose-HPAC_CPR1_polished | #135 | |
| 0.166 | cpr1_cbq_matched8 | #133 | |
| 0.172 | semantic-pose-HPAC_CPR1 | #130 | |
| 0.187 | rhnerv_latent_polish | #128 | |
| 0.190 | qlp_exactgrid | #129 | |
| 0.191 | qlp_exactgrid | #127 | |
| 0.191 | hnerv_qlp | #125 | |
| 0.191 | rhnerv_comma | #112 | |
| 0.192 | hnerv_fec6_fixed_huffman_k16 | #110 | |
| 0.193 | hnerv_ft_microcodec 👑 | #101 | |
| 0.195 | hnerv_lc_ac 👑 | #103 | |
| 0.195 | hnerv_lc_v2_scale095_rplus1 👑 | #102 | |
| 0.195 | hnerv_lc_v2 💡 | #100 | |
| 0.197 | hnerv_muon_finetuned_from_pr95 | #98 | |
| 0.198 | kitchen_sink | #105 | |
| 0.199 | hnerv_muon 💡 📖 | #95 | |
| 0.206 | rem2_HNeRV | #96 | |
| 0.209 | belt_and_suspenders | #106 | |
| 0.229 | vibe_coder_final_boss | #97 | |
| 0.229 | apogee | #107 | |
| 0.231 | qhnerv_ft_best | #104 | |
| 0.249 | hpac_coder_hybrid | #91 | |
| 0.258 | adaptive_masking_joint_frame_model | #85 | |
| 0.260 | qzs3_range_joint_r258 | #92 | |
| 0.274 | jas0xf_adversarial_neural_representation 💡 | #86 | |
| 0.275 | adaptive_range_mask | #84 | |
| 0.280 | qrepro 💡 | #90 | |
| 0.288 | qzs3_range_mask 💡 | #81 | |
| 0.315 | qpose14_r55_segactions_minp | #79 | |
| 0.315 | qzs3_tile_delta_r147 | #77 | |
| 0.316 | qpose14_qzs3_filmq9g_slsb1_r55 | #67 | |
| 0.320 | henosis_qz_n3z_r25_clean | #65 | |
| 0.321 | flatpup | #93 | |
| 0.325 | qpose14 | #63 | |
| 0.331 | unified_brotli | #64 | |
| 0.333 | quantizr 💡 | #55 | |
| 0.344 | qpose14_poseq6 | #76 | |
| 0.368 | ph4ntom_drv | #74 | |
| 0.375 | fp4_mask_gen | #62 | |
| 0.382 | selfcomp | #56 | |
| 0.481 | roro_perframe_hnerv | #119 | |
| 0.602 | mask2mask 💡 | #53 | |
| 0.717 | tomasdousek | #71 | |
| 1.236 | codex_metric_yshift_av1 💡 | #60 | |
| 1.891 | neural_inflate 💡 | #49 | |
| 1.914 | svtav1_dilated_ren | #58 | |
| 1.944 | roi_v2 | #48 | |
| 1.947 | av1_roi_lanczos_unsharp | #31 | |
| 1.979 | svtav1_av1grain_10bit | #51 | |
| 1.981 | damir_bearclaw_002 💡 | #30 | |
| 2.005 | roi_gop300_c34 | #43 | |
| 2.020 | v4_qp_aq2_roi 💡 | #44 | |
| 2.033 | av1_crf31_bicubic | #52 | |
| 2.052 | svtav1_cheetah | #24 | |
| 2.070 | svtav1_45pct_unsharp20_direct | #27 | |
| 2.083 | svtav1_gop360_binomial_unsharp | #26 | |
| 2.083 | av1_sharp1_adaptive | #23 | |
| 2.086 | svtav1_45pct_unsharp 💡 | #20 | |
| 2.158 | svtav1_spline_fg22 | #37 | |
| 2.200 | svt_av1_lanczos_fg | #18 | |
| 2.553 | h265_g16_512x384_veryslow | #21 | |
| 3.323 | optimized | #22 | |
| 3.833 | delta_codec 💡 | #61 | |
| 4.390 | baseline_fast | #1 | |
| 5.086 | damir_bearclaw_003 | #39 | |
| 25.000 | no_compress | #0 |
| score | name | method | |
|---|---|---|---|
| 4.0 | pmazumder3927 | arithmetic coding with commavq-gpt2m | |
| 4.0 | JPL11 | arithmetic coding with commavq-gpt2m | |
| 3.7 | mune-io | arithmetic coding with commavq-gpt2m | |
| 3.4 | szabolcs-cs | self-compressing neural network | |
| 3.0 | SAT-oO | arithmetic coding with GPT | |
| 2.9 | BradyWynn | arithmetic coding with GPT | |
| 2.8 | adelkordi42-png | arithmetic coding with GPT | |
| 2.7 | ylevental | arithmetic coding with GPT | |
| 2.7 | ksd3 | arithmetic coding with GPT | |
| 2.6 | pkourouklidis 👑 | arithmetic coding with GPT | |
| 2.3 | anonymous | zpaq | |
| 2.3 | rostislav | zpaq | |
| 2.2 | anonymous | zpaq | |
| 2.2 | anonymous | zpaq | |
| 2.2 | 0x41head | zpaq | |
| 2.2 | tillinf | zpaq | |
| 2.2 | ylevental | zpaq | |
| 2.2 | nuniesmith | zpaq | |
| 1.6 | baseline | lzma |
$1000 prize - first submission with >21 bugs found CLAIMED by LK!
$1000 prize - highest score by 6/22 (must be >22) CLAIMED by AnasMalas!
| bugs | name | |
|---|---|---|
| 24 | AnasMalas 👑 | |
| 24 | LK 👑 | |
| 23 | Milind220 | |
| 22 | BradyMeighan | |
| 21 | leosteinberg 👑 | |
| 21 | ProtonDev-sys | |
| 21 | DoubleGate | |
| 20 | probablyanasian | |
| 20 | delat | |
| 20 | i2cjak | |
| 20 | kumpulak | |
| 20 | daulet | |
| 20 | maddiedreese | |
| 19 | johannes-ece | |
| 19 | everythingapplejj | |
| 19 | MichaelIbrahim-GaTech | |
| 18 | MastroGippo | |
| 18 | dzid26 | |
| 18 | LukasCollishawM | |
| 18 | reformedot | |
| 18 | kaileh57 | |
| 18 | zacks-lab | |
| 18 | UberMetroid | |
| 18 | un-tag | |
| 18 | JX5S | |
| 18 | Champsmatter | |
| 17 | s-bashar | |
| 17 | gatordevin | |
| 17 | HueCodes | |
| 16 | ruselec 👑 | |
| 16 | ashrey | |
| 16 | 1kuna | |
| 16 | eyonce | |
| 16 | abhay | |
| 16 | eerwitt | |
| 15 | bjkayani | |
| 15 | 0rln | |
| 15 | kattaliraees | |
| 15 | epowell40 | |
| 15 | ganeshpimpale | |
| 15 | shellshock9001 | |
| 15 | vedantsaran |
| score | name | method | |
|---|---|---|---|
| 6.880 | RyanL2 👑 | per segment direct quadratic optimization | |
| 6.880 | hypery11 👑 | per segment direct quadratic optimization | |
| 6.880 | pmazumder3927 👑 | per segment direct quadratic optimization | |
| 7.083 | Vansh404 | online simulator probing with rng reset | |
| 7.228 | Yezus69 | per segment optimized actions | |
| 13.593 | auriium2 | per segment MPC | |
| 16.372 | Ashray-g | per segment optimized actions | |
| 17.791 | tfpgh | PGTO+BC distillation | |
| 19.620 | Hi9173 | online simulator probing with rng reset | |
| 21.435 | Chep-koech | per segment optimized actions | |
| 29.371 | nurikserikbayev | per segment optimized actions | |
| 29.549 | hypery11 | per segment optimized actions | |
| 33.595 | JasonMo123 | CEM MPC+BC transformer | |
| 35.967 | haraschax | MPC+much compute | |
| 39.348 | ksd3 | per segment MPC | |
| 41.730 | dynm | per-segment optimized blended controllers | |
| 42.206 | utkarshgill | PPO+MPC | |
| 44.320 | kaileh57 | Gauss-Newton MPC | |
| 45.756 | bheijden | PPO | |
| 46.92 | Janaa19 | per segment PID+FF with CEM | |
| 48.08 | ellenjxu | custom feedback controller + evolution | |
| 48.474 | TheConverseEngineer | tube MPC + 2dof PID | |
| 48.57 | Quantizr | custom feedback controller | |
| 49.264 | dumanah | MPC w diffusion style annealing | |
| 50.192 | truefit-ai | custom PID + evolution | |
| 50.608 | CheckmeowwwT | PID w FF | |
| 50.633 | jonoomph | ML PID | |
| 50.716 | felsager 👑 | custom feedback controller | 51.483 | AnmolDeshmukh | Adaptive preview PID+CMA-ES |
| 52.114 | Jerenemy | Residual preview MPC | |
| 52.506 | izzunnafis | custom feedback controller | |
| 53.050 | Josemedinan | custom feedback controller | |
| 54.708 | ch33nchan | adaptive PID | |
| 54.709 | freeklinssen | adaptive PID | |
| 55.485 | garrettpall | custom feedback controller | |
| 55.739 | clouds1729 | custom feedback controller + evolution | |
| 56.586 | AnmolDeshmukh | PID w FF | |
| 56.849 | armanjr | PID w FF | |
| 57.670 | YasinSonmez | PID w FF | |
| 58.57 | YashDYD | custom feedback controller | |
| 59.317 | Parth171 | custom feedback controller | |
| 59.811 | avangerp | custom feedback controller | |
| 59.853 | haraschax | custom feedback controller | |
| 59.862 | tristan-yk | PID w FF | |
| 60.993 | srikanth-444 | PPO | |
| 61.783 | xfqbuaa | custom PID | |
| 62.462 | 0xmmo | genetic algorithm | |
| 62.971 | zachhaidari | PID w FF | |
| 63.793 | fabP258 | DOBC | |
| 64.042 | avlord | PID w FF | |
| 66.165 | CheckmeowwwT | PID w FF | |
| 67.329 | ninohdasilva | PID w FF | |
| 67.355 | kofteee | adaptive PID | |
| 68.055 | matthiaspetry | custom feedback controller | |
| 68.942 | Officially-Siddhant | custom PID | |
| 69.100 | Vansh404 | custom feedback controller + bayesian optimization | |
| 74.440 | diegoruizpon | custom feedback controller | |
| 75.688 | Sanjit1 | custom feedback controller | |
| 76.644 | jaumebalust | PID w FF | |
| 76.723 | gcosentino | PID w FF | |
| 77.365 | ZiZizou | custom PID | |
| 77.411 | chinmayi-r | >PID w FF | |
| 78.590 | hpoonawala | PID w FF | |
| 78.593 | Havee005 | PID w FF | |
| 78.862 | hbarkh | PID w FF | |
| 78.868 | yiannisha | bayesian optimization | |
| 79.316 | chinmaymirji | PID+TD3 | |
| 79.360 | ffmiruz | MPC | |
| 80.828 | donymorph | custom PID | |
| 83.568 | jonoomph8 | custom PID | |
| 88.774 | Pranav-Malpure | custom PID | |
| 90.893 | atharva10764 | custom PID w FF | |
| 91.130 | integ01 | MPC | |
| 95.724 | adhintz | auto-tuned PID | |
| 98.703 | QuangTran1608 | slsqp | |
| 100.445 | pau-mensa | bayesian optimization | |
| 102.184 | NikhilGangaram | custom PID | |
| 110.254 | baseline | PID |
| score | name | |
|---|---|---|
| 5.33% | fredyshox | |
| 9.4% | Boris | |
| 10.0% | krikarls | |
| 11.4% | Ritam | |
| 18.5% | bongbui321 | |
| 18.7% | Nathan | |
| 19.0% | MartinEthier | |
| 19.0% | louislva | |
| 19.6% | arshsinghal6 | |
| 19.6% | Yasin | |
| 20.0% | RoyVorster | |
| 20.0% | Roman | |
| 20.22% | Armandpl | |
| 20.5% | Herman | |
| 24.8% | gijskoning |