HIPE-2026 Evaluation Results (Binary at)

This file is generated from results-binary.d/system-rankings/*.tsv.

Teams

team name affiliation
baseline Ministral-3-3B-Instruct GGUF baseline 0.2.2 random seed 42 HIPE-2026 organizers
random Random Decision Baseline HIPE-2026 organizers
team1 Awakened National University of Science and Technology Politehnica Bucharest
team10 BIU_NLP Bar-Ilan University
team11 gipplab University of Göttingen
team12 whereami Alexandria University
team13 Spinfo Universität zu Köln
team14 MILRIT University of Toulouse & La Rochelle University
team15 FI-CODE University of the Bundeswehr Munich
team16 Rittik&Souvik Jadavpur University, Kolkata
team17 INSA Lyon INSA Lyon - University of Lyon
team2 DS@GT_HIPE Georgia Institute of Technology
team3 VerbaNexAI II Universidad Tecnológica de Bolívar
team4 FourBytes Sri Sivasubramaniya Nadar College of Engineering
team5 UMUTEAM Universidad de Murcia
team6 VerbaNexAI I Universidad Tecnológica de Bolívar
team7 ROSTI Université Lumière Lyon
team8 MaxFo-Ajie Foshan University
team9 Hansel&Gretel IIT Roorkee

Table of Contents

Profile Score Definitions

  • Accuracy Profile Ranking uses the impresso test files.
  • Generalization Profile Ranking uses the surprise test files.
  • For a label l, recall_l = true_positives_l / gold_instances_l.
  • This binary report maps PROBABLE to TRUE for at in both reference and system labels.
  • at_macro_recall = mean(recall_TRUE, recall_FALSE) for the binarized at labels.
  • isAt_macro_recall = mean(recall_TRUE, recall_FALSE) for the isAt labels.
  • impresso_profile_score: score for one impresso language file, computed as the mean of at_macro_recall and isAt_macro_recall.
  • mean_impresso_profile_score: mean of impresso_profile_score over the submitted impresso language files.
  • surprise_profile_score: score on a surprise file, computed as at_macro_recall; isAt is not evaluated for surprise.
  • Accuracy columns are included as contextual diagnostics; ranking is still determined by the macro-recall profile score.
  • mean_efficiency_profile_rank: mean of rank_impresso_profile_score, rank_hipe_parameter_count, and rank_hipe_model_size; lower is better.
  • balanced_efficiency_profile_rank: 0.5 * rank_impresso_profile_score + 0.25 * rank_hipe_parameter_count + 0.25 * rank_hipe_model_size; lower is better.
  • If team_efficiency_opt_out=true in a run’s *-info.json, that run is excluded from efficiency ranking tables.
  • If organizer fields hipe_parameter_count or hipe_model_size are null, they are internally treated as maxint for efficiency rank computation (worst resource rank), while remaining empty in table outputs.

Accuracy Profile Ranking Overall

rank team run mean impresso profile score languages num language files
1 team13 run1 0.8419 de,en,fr 3
2 team13 run3 0.8369 de,en,fr 3
3 team12 run2 0.8156 de,en,fr 3
4 team12 run1 0.8148 de,en,fr 3
5 team13 run2 0.7998 de,en,fr 3
6 team1 run3 0.7925 de,en,fr 3
7 team8 run1 0.788 de,en,fr 3
8 team1 run1 0.7862 de,en,fr 3
9 team8 run2 0.7701 de,en,fr 3
10 team17 run1 0.7629 de,en,fr 3
11 team8 run3 0.76 de,en,fr 3
12 team11 run2 0.739 de,en,fr 3
13 team9 run3 0.7284 de,en,fr 3
14 team11 run1 0.7198 de,en,fr 3
15 team5 run2 0.7052 de,en,fr 3
16 team3 run3 0.6864 de,en,fr 3
17 baseline run1 0.6818 de,en,fr 3
18 team14 run3 0.6782 de,en,fr 3
19 team9 run2 0.6765 de,en,fr 3
20 team10 run2 0.6721 de,en,fr 3
21 team14 run1 0.6653 de,en,fr 3
22 team1 run2 0.6558 de,en,fr 3
23 team9 run1 0.6539 de,en,fr 3
24 team10 run3 0.6274 de,en,fr 3
25 team3 run2 0.6259 de,en,fr 3
26 team11 run3 0.6145 de,en,fr 3
27 team2 run1 0.6065 de,en,fr 3
28 team3 run1 0.6005 de,en,fr 3
29 team17 run2 0.5853 de,en,fr 3
30 team2 run2 0.5819 de,en,fr 3
31 team17 run3 0.576 de,en,fr 3
32 team15 run2 0.5664 de,en,fr 3
33 team6 run2 0.5633 de,en,fr 3
34 team2 run3 0.5562 de,en,fr 3
35 team6 run1 0.5544 de,en,fr 3
36 team15 run3 0.5493 de,en,fr 3
37 team7 run3 0.5484 de,en,fr 3
38 team5 run3 0.5426 de,en,fr 3
39 team7 run2 0.5374 de,en,fr 3
40 team7 run1 0.5338 de,en,fr 3
41 team10 run1 0.5252 de,en,fr 3
42 team5 run1 0.5245 de,en,fr 3
43 team15 run1 0.5215 de,en,fr 3
44 team14 run2 0.5155 de,en,fr 3
45 team4 run1 0.4988 de,en,fr 3
46 random run1 0.4913 de,en,fr 3

Top 3 teams by best run:

  1. Spinfo (team13), run1, table rank 1, mean impresso profile score 0.8419
  2. whereami (team12), run2, table rank 3, mean impresso profile score 0.8156
  3. Awakened (team1), run3, table rank 6, mean impresso profile score 0.7925

Only team runs that submitted all impresso language files are included in this overall ranking. Team runs with partial submissions are shown only in the dataset-specific ranking tables.

Accuracy Profile Ranking German

rank team run submission impresso profile score at macro recall at accuracy isAt macro recall isAt accuracy diagnostics
1 team13 run3 team13_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.8721 0.9048 0.9202 0.8394 0.8866 Comparison / Metrics
2 team13 run1 team13_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.8599 0.8999 0.9118 0.8199 0.8782 Comparison / Metrics
3 team12 run1 team12_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.8508 0.8862 0.895 0.8154 0.8782 Comparison / Metrics
4 team12 run2 team12_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.8472 0.8911 0.9034 0.8034 0.8739 Comparison / Metrics
5 team17 run1 team17_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.8209 0.7922 0.8067 0.8497 0.8361 Comparison / Metrics
6 team1 run1 team1_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.8088 0.8556 0.8277 0.7621 0.8277 Comparison / Metrics
7 team1 run3 team1_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.8071 0.8644 0.8361 0.7498 0.8361 Comparison / Metrics
8 team8 run1 team8_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.7885 0.8379 0.8529 0.7391 0.8403 Comparison / Metrics
9 team13 run2 team13_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.7866 0.8671 0.8739 0.706 0.8319 Comparison / Metrics
10 team5 run2 team5_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.7562 0.7744 0.7479 0.738 0.7605 Comparison / Metrics
11 team8 run2 team8_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.7395 0.7967 0.8319 0.6823 0.8109 Comparison / Metrics
12 team8 run3 team8_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.7387 0.7967 0.8319 0.6807 0.8151 Comparison / Metrics
13 team11 run2 team11_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.7345 0.8868 0.8908 0.5821 0.7647 Comparison / Metrics
14 team11 run1 team11_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.7216 0.8387 0.8613 0.6045 0.7773 Comparison / Metrics
15 team9 run3 team9_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.7166 0.7219 0.7353 0.7112 0.8067 Comparison / Metrics
16 team14 run3 team14_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.692 0.7408 0.7017 0.6433 0.7353 Comparison / Metrics
17 team14 run1 team14_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.6885 0.6918 0.7353 0.6852 0.7563 Comparison / Metrics
18 team3 run3 team3_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.6621 0.7149 0.7563 0.6093 0.7647 Comparison / Metrics
19 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.6578 0.7028 0.7143 0.6129 0.7437 Comparison / Metrics
20 team9 run1 team9_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.655 0.7831 0.7857 0.5269 0.7311 Comparison / Metrics
21 team9 run2 team9_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.646 0.7575 0.7395 0.5344 0.7353 Comparison / Metrics
22 team1 run2 team1_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.6455 0.7027 0.6723 0.5882 0.7605 Comparison / Metrics
23 team10 run3 team10_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.6381 0.6312 0.6807 0.645 0.7899 Comparison / Metrics
24 team10 run2 team10_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.6231 0.7102 0.7185 0.536 0.7311 Comparison / Metrics
25 team11 run3 team11_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.6192 0.7115 0.7521 0.5269 0.7311 Comparison / Metrics
26 team7 run3 team7_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.6158 0.6175 0.6639 0.6141 0.6933 Comparison / Metrics
27 team2 run1 team2_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.6139 0.6235 0.6639 0.6043 0.6597 Comparison / Metrics
28 team3 run2 team3_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.6102 0.7038 0.7353 0.5165 0.7227 Comparison / Metrics
29 team7 run1 team7_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.6094 0.6106 0.6555 0.6082 0.6849 Comparison / Metrics
30 team7 run2 team7_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.6031 0.6038 0.6471 0.6024 0.6765 Comparison / Metrics
31 team2 run2 team2_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.592 0.5861 0.5588 0.5978 0.6765 Comparison / Metrics
32 team6 run2 team6_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.5885 0.5847 0.5546 0.5923 0.6555 Comparison / Metrics
33 team3 run1 team3_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.5795 0.6358 0.6765 0.5233 0.6933 Comparison / Metrics
34 team2 run3 team2_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.5782 0.5661 0.6008 0.5904 0.6723 Comparison / Metrics
35 team17 run2 team17_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.5707 0.6336 0.6639 0.5078 0.7101 Comparison / Metrics
36 team15 run2 team15_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.5598 0.5746 0.5126 0.545 0.4244 Comparison / Metrics
37 team5 run3 team5_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.553 0.5542 0.458 0.5517 0.395 Comparison / Metrics
38 team6 run1 team6_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.5503 0.5517 0.5042 0.5488 0.6387 Comparison / Metrics
39 team17 run3 team17_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.549 0.572 0.6303 0.5261 0.5798 Comparison / Metrics
40 team10 run1 team10_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.5329 0.5435 0.6471 0.5224 0.7311 Comparison / Metrics
41 team15 run1 team15_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.532 0.564 0.5588 0.5 0.7185 Comparison / Metrics
42 team15 run3 team15_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 0.5187 0.5237 0.6303 0.5136 0.7185 Comparison / Metrics
43 team14 run2 team14_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 0.5167 0.511 0.5924 0.5224 0.7311 Comparison / Metrics
44 team5 run1 team5_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.5 0.5 0.6134 0.5 0.7185 Comparison / Metrics
45 team4 run1 team4_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.4906 0.4818 0.416 0.4995 0.6134 Comparison / Metrics
46 random run1 random_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 0.4783 0.4661 0.4412 0.4906 0.4832 Comparison / Metrics

Top 3 teams by best run:

  1. Spinfo (team13), run3, table rank 1, impresso profile score 0.8721
  2. whereami (team12), run1, table rank 3, impresso profile score 0.8508
  3. INSA Lyon (team17), run1, table rank 5, impresso profile score 0.8209

Accuracy Profile Ranking English

rank team run submission impresso profile score at macro recall at accuracy isAt macro recall isAt accuracy diagnostics
1 team8 run1 team8_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.8102 0.8642 0.8642 0.7562 0.7901 Comparison / Metrics
2 team12 run2 team12_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.8058 0.8194 0.821 0.7921 0.821 Comparison / Metrics
3 team13 run1 team13_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.803 0.8061 0.8086 0.7998 0.8272 Comparison / Metrics
4 team8 run2 team8_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.8024 0.8897 0.8827 0.7151 0.7531 Comparison / Metrics
5 team13 run3 team13_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.8016 0.8291 0.8333 0.7741 0.8025 Comparison / Metrics
6 team12 run1 team12_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.7982 0.8145 0.8148 0.7819 0.8148 Comparison / Metrics
7 team8 run3 team8_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.7875 0.8521 0.858 0.7229 0.7654 Comparison / Metrics
8 team13 run2 team13_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.7605 0.8569 0.8457 0.664 0.7222 Comparison / Metrics
9 team1 run3 team1_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.7471 0.8122 0.8395 0.682 0.7407 Comparison / Metrics
10 team9 run3 team9_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.7279 0.7406 0.7346 0.7151 0.7531 Comparison / Metrics
11 team1 run1 team1_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.7138 0.7868 0.821 0.6408 0.6914 Comparison / Metrics
12 team11 run2 team11_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.7119 0.7674 0.7963 0.6564 0.7222 Comparison / Metrics
13 team17 run1 team17_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.7031 0.6837 0.7037 0.7225 0.7346 Comparison / Metrics
14 team11 run1 team11_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.696 0.7176 0.7284 0.6743 0.7346 Comparison / Metrics
15 team3 run3 team3_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.6841 0.7453 0.7037 0.623 0.6914 Comparison / Metrics
16 team9 run2 team9_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.6803 0.6887 0.7469 0.6718 0.7346 Comparison / Metrics
17 team3 run1 team3_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.6786 0.7068 0.7469 0.6504 0.6543 Comparison / Metrics
18 team9 run1 team9_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.6645 0.6983 0.7222 0.6308 0.7037 Comparison / Metrics
19 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.6638 0.6945 0.6852 0.6331 0.6852 Comparison / Metrics
20 team3 run2 team3_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.6566 0.7261 0.7346 0.5871 0.6605 Comparison / Metrics
21 team10 run2 team10_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.6524 0.633 0.6852 0.6718 0.7346 Comparison / Metrics
22 team14 run3 team14_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.6351 0.604 0.6852 0.6663 0.7037 Comparison / Metrics
23 team5 run2 team5_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.6315 0.6282 0.6975 0.6349 0.6296 Comparison / Metrics
24 team17 run2 team17_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.6247 0.6752 0.679 0.5741 0.642 Comparison / Metrics
25 team11 run3 team11_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.6209 0.6316 0.642 0.6102 0.6852 Comparison / Metrics
26 team17 run3 team17_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.613 0.612 0.5802 0.6141 0.5926 Comparison / Metrics
27 team2 run1 team2_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.6044 0.5867 0.5988 0.6221 0.6235 Comparison / Metrics
28 team10 run3 team10_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.5904 0.6193 0.5988 0.5615 0.6481 Comparison / Metrics
29 team1 run2 team1_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.5889 0.5193 0.6235 0.6586 0.6975 Comparison / Metrics
30 team14 run1 team14_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.5756 0.5782 0.5926 0.573 0.5556 Comparison / Metrics
31 team2 run3 team2_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.5673 0.531 0.5556 0.6036 0.5679 Comparison / Metrics
32 team15 run2 team15_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.5529 0.5592 0.642 0.5467 0.4815 Comparison / Metrics
33 team6 run1 team6_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.5511 0.4803 0.537 0.622 0.6173 Comparison / Metrics
34 team6 run2 team6_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.5451 0.4985 0.5741 0.5916 0.6173 Comparison / Metrics
35 team5 run1 team5_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.5445 0.5191 0.5864 0.5699 0.5123 Comparison / Metrics
36 team10 run1 team10_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.5382 0.5559 0.4444 0.5205 0.6111 Comparison / Metrics
37 team2 run2 team2_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.5317 0.554 0.5617 0.5095 0.5494 Comparison / Metrics
38 team7 run3 team7_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.5307 0.5415 0.463 0.52 0.5741 Comparison / Metrics
39 team14 run2 team14_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.5267 0.5329 0.4383 0.5205 0.6111 Comparison / Metrics
40 team7 run2 team7_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 0.518 0.5366 0.4568 0.4994 0.5556 Comparison / Metrics
41 team15 run1 team15_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.518 0.536 0.5988 0.5 0.5988 Comparison / Metrics
42 team5 run3 team5_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.5143 0.4951 0.6296 0.5335 0.4444 Comparison / Metrics
43 team15 run3 team15_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 0.5126 0.4571 0.4938 0.568 0.5617 Comparison / Metrics
44 team7 run1 team7_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.5042 0.5245 0.4506 0.484 0.537 Comparison / Metrics
45 team4 run1 team4_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.497 0.4951 0.6296 0.4989 0.5123 Comparison / Metrics
46 team16 run1 team16_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.4939 0.4628 0.4136 0.5249 0.5617 Comparison / Metrics
47 random run1 random_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 0.462 0.4305 0.4691 0.4935 0.4877 Comparison / Metrics

Top 3 teams by best run:

  1. MaxFo-Ajie (team8), run1, table rank 1, impresso profile score 0.8102
  2. whereami (team12), run2, table rank 2, impresso profile score 0.8058
  3. Spinfo (team13), run1, table rank 3, impresso profile score 0.803

Accuracy Profile Ranking French

rank team run submission impresso profile score at macro recall at accuracy isAt macro recall isAt accuracy diagnostics
1 team13 run1 team13_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.8628 0.8938 0.895 0.8318 0.8529 Comparison / Metrics
2 team13 run2 team13_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.8523 0.9056 0.9034 0.7991 0.8571 Comparison / Metrics
3 team13 run3 team13_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.837 0.8607 0.8613 0.8132 0.8403 Comparison / Metrics
4 team1 run1 team1_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.836 0.9237 0.9202 0.7483 0.7941 Comparison / Metrics
5 team1 run3 team1_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.8232 0.9285 0.9244 0.7179 0.7815 Comparison / Metrics
6 team12 run1 team12_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7955 0.851 0.8613 0.74 0.8067 Comparison / Metrics
7 team12 run2 team12_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7939 0.851 0.8613 0.7368 0.8025 Comparison / Metrics
8 team11 run2 team11_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7706 0.8965 0.8992 0.6448 0.7521 Comparison / Metrics
9 team8 run2 team8_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7684 0.827 0.8403 0.7099 0.8025 Comparison / Metrics
10 team8 run1 team8_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7654 0.8271 0.8319 0.7037 0.7983 Comparison / Metrics
11 team17 run1 team17_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7648 0.7149 0.7311 0.8147 0.8067 Comparison / Metrics
12 team8 run3 team8_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.7539 0.835 0.8529 0.6728 0.7773 Comparison / Metrics
13 team11 run1 team11_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7418 0.8078 0.8235 0.6758 0.7773 Comparison / Metrics
14 team10 run2 team10_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7409 0.7462 0.7227 0.7356 0.7773 Comparison / Metrics
15 team9 run3 team9_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.7409 0.748 0.7647 0.7338 0.8025 Comparison / Metrics
16 team1 run2 team1_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7329 0.7904 0.7773 0.6754 0.7689 Comparison / Metrics
17 team14 run1 team14_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7318 0.7448 0.7563 0.7187 0.7353 Comparison / Metrics
18 team5 run2 team5_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7278 0.7254 0.7017 0.7302 0.7269 Comparison / Metrics
19 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.7239 0.7674 0.7647 0.6804 0.7479 Comparison / Metrics
20 team3 run3 team3_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.713 0.7944 0.8109 0.6316 0.7269 Comparison / Metrics
21 team14 run3 team14_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.7074 0.7402 0.7353 0.6746 0.7521 Comparison / Metrics
22 team9 run2 team9_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.7033 0.793 0.7899 0.6137 0.7269 Comparison / Metrics
23 team10 run3 team10_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.6538 0.7584 0.7437 0.5492 0.6891 Comparison / Metrics
24 team9 run1 team9_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.642 0.7133 0.7269 0.5707 0.7017 Comparison / Metrics
25 team2 run2 team2_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.6219 0.6249 0.6261 0.6189 0.6471 Comparison / Metrics
26 team15 run3 team15_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.6165 0.6261 0.6092 0.607 0.584 Comparison / Metrics
27 team3 run2 team3_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.611 0.71 0.7353 0.512 0.6597 Comparison / Metrics
28 team11 run3 team11_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.6033 0.6513 0.6849 0.5554 0.6933 Comparison / Metrics
29 team2 run1 team2_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.6012 0.5669 0.5462 0.6354 0.6807 Comparison / Metrics
30 team15 run2 team15_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.5865 0.5927 0.5462 0.5802 0.458 Comparison / Metrics
31 team17 run3 team17_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.5658 0.5311 0.5714 0.6004 0.6345 Comparison / Metrics
32 team6 run1 team6_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5619 0.5555 0.5504 0.5683 0.6513 Comparison / Metrics
33 team17 run2 team17_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.5606 0.6134 0.6387 0.5078 0.6345 Comparison / Metrics
34 team5 run3 team5_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.5605 0.5442 0.4916 0.5768 0.4496 Comparison / Metrics
35 team6 run2 team6_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.5564 0.5356 0.4916 0.5773 0.6513 Comparison / Metrics
36 team3 run1 team3_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5433 0.5697 0.5966 0.5169 0.6387 Comparison / Metrics
37 random run1 random_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5334 0.5407 0.5252 0.5262 0.5168 Comparison / Metrics
38 team5 run1 team5_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.529 0.5613 0.5714 0.4967 0.5882 Comparison / Metrics
39 team2 run3 team2_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.5231 0.5753 0.563 0.4708 0.4832 Comparison / Metrics
40 team15 run1 team15_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5144 0.5288 0.5252 0.5 0.6597 Comparison / Metrics
41 team4 run1 team4_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5088 0.512 0.4832 0.5056 0.5882 Comparison / Metrics
42 team10 run1 team10_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.5044 0.5059 0.5672 0.503 0.6597 Comparison / Metrics
43 team14 run2 team14_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.5031 0.5194 0.563 0.4869 0.6345 Comparison / Metrics
44 team7 run3 team7_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 0.4987 0.487 0.5084 0.5104 0.563 Comparison / Metrics
45 team7 run2 team7_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 0.491 0.4742 0.5 0.5078 0.5714 Comparison / Metrics
46 team7 run1 team7_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 0.4877 0.4774 0.5 0.4981 0.5546 Comparison / Metrics

Top 3 teams by best run:

  1. Spinfo (team13), run1, table rank 1, impresso profile score 0.8628
  2. Awakened (team1), run1, table rank 4, impresso profile score 0.836
  3. whereami (team12), run1, table rank 6, impresso profile score 0.7955

Generalization Profile Ranking

rank team run submission surprise profile score diagnostics
1 team8 run1 team8_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.9182 Comparison / Metrics
1 team8 run3 team8_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.9182 Comparison / Metrics
2 team8 run2 team8_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.9163 Comparison / Metrics
3 team10 run1 team10_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8804 Comparison / Metrics
4 team13 run1 team13_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8764 Comparison / Metrics
5 team13 run2 team13_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8688 Comparison / Metrics
6 team13 run3 team13_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.8667 Comparison / Metrics
7 team12 run2 team12_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8557 Comparison / Metrics
8 team11 run2 team11_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8546 Comparison / Metrics
9 team1 run3 team1_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.852 Comparison / Metrics
10 team1 run1 team1_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8485 Comparison / Metrics
11 team12 run1 team12_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8461 Comparison / Metrics
12 team11 run1 team11_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8357 Comparison / Metrics
13 team9 run3 team9_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.832 Comparison / Metrics
14 team3 run3 team3_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.8034 Comparison / Metrics
15 team9 run1 team9_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.7972 Comparison / Metrics
16 team9 run2 team9_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.794 Comparison / Metrics
17 team11 run3 team11_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.7444 Comparison / Metrics
18 team3 run2 team3_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7425 Comparison / Metrics
19 team14 run3 team14_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.727 Comparison / Metrics
20 team10 run3 team10_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.7262 Comparison / Metrics
21 team1 run2 team1_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7237 Comparison / Metrics
22 team5 run2 team5_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7207 Comparison / Metrics
23 team17 run1 team17_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.712 Comparison / Metrics
24 team14 run1 team14_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6909 Comparison / Metrics
25 baseline run1 baseline_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6678 Comparison / Metrics
26 team10 run2 team10_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.6473 Comparison / Metrics
27 team3 run1 team3_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6368 Comparison / Metrics
28 team17 run2 team17_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.6158 Comparison / Metrics
29 team2 run3 team2_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5777 Comparison / Metrics
30 team14 run2 team14_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5743 Comparison / Metrics
31 team17 run3 team17_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5715 Comparison / Metrics
32 team6 run2 team6_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5608 Comparison / Metrics
33 team15 run2 team15_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5596 Comparison / Metrics
34 team7 run1 team7_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5593 Comparison / Metrics
35 team15 run1 team15_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5583 Comparison / Metrics
36 team7 run3 team7_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5557 Comparison / Metrics
37 team7 run2 team7_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5533 Comparison / Metrics
38 team2 run2 team2_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5492 Comparison / Metrics
39 random run1 random_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5344 Comparison / Metrics
40 team15 run3 team15_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5265 Comparison / Metrics
41 team2 run1 team2_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.523 Comparison / Metrics
42 team4 run1 team4_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5118 Comparison / Metrics
42 team6 run1 team6_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5118 Comparison / Metrics
43 team5 run3 team5_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5026 Comparison / Metrics
44 team5 run1 team5_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5 Comparison / Metrics

Top 3 teams by best run:

  1. MaxFo-Ajie (team8), run1, table rank 1, surprise profile score 0.9182
  2. BIU_NLP (team10), run1, table rank 3, surprise profile score 0.8804
  3. Spinfo (team13), run1, table rank 4, surprise profile score 0.8764

Generalization Profile Ranking French

rank team run submission surprise profile score at macro recall at accuracy diagnostics
1 team8 run1 team8_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.9182 0.9182 0.9187 Comparison / Metrics
1 team8 run3 team8_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.9182 0.9182 0.9187 Comparison / Metrics
2 team8 run2 team8_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.9163 0.9163 0.9208 Comparison / Metrics
3 team10 run1 team10_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8804 0.8804 0.8917 Comparison / Metrics
4 team13 run1 team13_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8764 0.8764 0.8792 Comparison / Metrics
5 team13 run2 team13_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8688 0.8688 0.8667 Comparison / Metrics
6 team13 run3 team13_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.8667 0.8667 0.8729 Comparison / Metrics
7 team12 run2 team12_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8557 0.8557 0.875 Comparison / Metrics
8 team11 run2 team11_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.8546 0.8546 0.8583 Comparison / Metrics
9 team1 run3 team1_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.852 0.852 0.8354 Comparison / Metrics
10 team1 run1 team1_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8485 0.8485 0.8333 Comparison / Metrics
11 team12 run1 team12_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8461 0.8461 0.8667 Comparison / Metrics
12 team11 run1 team11_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.8357 0.8357 0.8562 Comparison / Metrics
13 team9 run3 team9_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.832 0.832 0.8354 Comparison / Metrics
14 team3 run3 team3_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.8034 0.8034 0.8271 Comparison / Metrics
15 team9 run1 team9_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.7972 0.7972 0.8021 Comparison / Metrics
16 team9 run2 team9_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.794 0.794 0.7708 Comparison / Metrics
17 team11 run3 team11_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.7444 0.7444 0.7646 Comparison / Metrics
18 team3 run2 team3_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7425 0.7425 0.7667 Comparison / Metrics
19 team14 run3 team14_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.727 0.727 0.7063 Comparison / Metrics
20 team10 run3 team10_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.7262 0.7262 0.6813 Comparison / Metrics
21 team1 run2 team1_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7237 0.7237 0.6979 Comparison / Metrics
22 team5 run2 team5_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.7207 0.7207 0.6833 Comparison / Metrics
23 team17 run1 team17_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.712 0.712 0.7375 Comparison / Metrics
24 team14 run1 team14_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6909 0.6909 0.7208 Comparison / Metrics
25 baseline run1 baseline_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6678 0.6678 0.6479 Comparison / Metrics
26 team10 run2 team10_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.6473 0.6473 0.5771 Comparison / Metrics
27 team3 run1 team3_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.6368 0.6368 0.6729 Comparison / Metrics
28 team17 run2 team17_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.6158 0.6158 0.675 Comparison / Metrics
29 team2 run3 team2_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5777 0.5777 0.5708 Comparison / Metrics
30 team14 run2 team14_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5743 0.5743 0.6271 Comparison / Metrics
31 team17 run3 team17_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5715 0.5715 0.65 Comparison / Metrics
32 team6 run2 team6_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5608 0.5608 0.5417 Comparison / Metrics
33 team15 run2 team15_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5596 0.5596 0.4854 Comparison / Metrics
34 team7 run1 team7_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5593 0.5593 0.5979 Comparison / Metrics
35 team15 run1 team15_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5583 0.5583 0.5375 Comparison / Metrics
36 team7 run3 team7_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5557 0.5557 0.5958 Comparison / Metrics
37 team7 run2 team7_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5533 0.5533 0.5896 Comparison / Metrics
38 team2 run2 team2_HIPE-2026-v1.0-surprise-test-fr_run2.jsonl 0.5492 0.5492 0.5583 Comparison / Metrics
39 random run1 random_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5344 0.5344 0.5021 Comparison / Metrics
40 team15 run3 team15_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5265 0.5265 0.5375 Comparison / Metrics
41 team2 run1 team2_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.523 0.523 0.4708 Comparison / Metrics
42 team4 run1 team4_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5118 0.5118 0.4167 Comparison / Metrics
42 team6 run1 team6_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5118 0.5118 0.5833 Comparison / Metrics
43 team5 run3 team5_HIPE-2026-v1.0-surprise-test-fr_run3.jsonl 0.5026 0.5026 0.4188 Comparison / Metrics
44 team5 run1 team5_HIPE-2026-v1.0-surprise-test-fr_run1.jsonl 0.5 0.5 0.6042 Comparison / Metrics

Top 3 teams by best run:

  1. MaxFo-Ajie (team8), run1, table rank 1, surprise profile score 0.9182
  2. BIU_NLP (team10), run1, table rank 3, surprise profile score 0.8804
  3. Spinfo (team13), run1, table rank 4, surprise profile score 0.8764

Efficiency Profile Ranking Overall

rank team run mean efficiency profile rank rank impresso profile score rank hipe parameter count rank hipe model size mean impresso profile score hipe parameter count hipe model size mb
1 team15 run2 10.3333 29 1 1 0.5664 0 0
2 team14 run3 10.6667 15 8 9 0.6782 277730309 1111
3 team2 run1 11 24 5 4 0.6065 2087375 87
4 team2 run2 12 27 5 4 0.5819 2087375 87
5 team2 run3 13.3333 31 5 4 0.5562 2087375 87
6 team14 run1 13.6667 18 12 11 0.6653 466577920 1780
6 team7 run1 13.6667 37 2 2 0.5338 12279 0.8
6 team7 run3 13.6667 34 4 3 0.5484 12399 0.81
7 team7 run2 14 36 3 3 0.5374 12365 0.81
8 team17 run2 14.3333 26 9 8 0.5853 278043651 1061
9 random run1 15 43 1 1 0.4913 0 0
10 team1 run2 15.3333 19 14 13 0.6558 560965127 2140
11 baseline run1 15.6667 14 19 14 0.6818 3000000000 2147.023
12 team12 run2 16.3333 3 22 24 0.8156 5123178979 9600
12 team3 run3 16.3333 13 20 16 0.6864 4000000000 2840
13 team12 run1 16.6667 4 22 24 0.8148 5123178979 9600
14 team15 run1 17 40 6 5 0.5215 208935168 816
14 team6 run2 17 30 11 10 0.5633 355000000 1424
15 team5 run1 17.3333 39 7 6 0.5245 270000000 1030
16 team11 run2 17.6667 9 21 23 0.739 4465470464 9012
16 team6 run1 17.6667 32 11 10 0.5544 355000000 1424
17 team5 run2 18 12 20 22 0.7052 4000000000 7600
18 team3 run1 18.6667 25 16 15 0.6005 1500000000 2340
19 team11 run3 19.3333 23 17 18 0.6145 1949101888 3845
20 team4 run1 19.6667 42 10 7 0.4988 278054405 1060
21 team17 run3 20 28 15 17 0.576 838778678 3217
21 team9 run1 20 20 19 21 0.6539 3000000000 6248
22 team13 run1 20.3333 1 30 30 0.8419 116830000000 65238
23 team11 run1 20.6667 11 25 26 0.7198 9300029952 18398
23 team13 run3 20.6667 2 30 30 0.8369 116830000000 65238
24 team13 run2 21.6667 5 30 30 0.7998 116830000000 65238
24 team3 run2 21.6667 22 23 20 0.6259 5900000000 5980
24 team9 run2 21.6667 16 24 25 0.6765 7000000000 15300
25 team14 run2 22 41 13 12 0.5155 466585989 1866
26 team17 run1 22.6667 8 29 31 0.7629 101927226758 195716
27 team15 run3 23.3333 33 18 19 0.5493 2274069824 4442
28 team1 run3 23.6667 6 32 33 0.7925 999999999999 999999
29 team1 run1 24 7 32 33 0.7862 999999999999 999999
30 team9 run3 24.3333 10 31 32 0.7284 120000000000 240000
31 team10 run2 24.6667 17 28 29 0.6721 27000000000 54000
31 team10 run3 24.6667 21 26 27 0.6274 24000000000 48000
32 team5 run3 25.6667 35 20 22 0.5426 4000000000 7600
33 team10 run1 31 38 27 28 0.5252 26000000000 52000

Top 3 teams by best run:

  1. FI-CODE (team15), run2, table rank 1, mean efficiency profile rank 10.3333
  2. MILRIT (team14), run3, table rank 2, mean efficiency profile rank 10.6667
  3. DS@GT_HIPE (team2), run1, table rank 3, mean efficiency profile rank 11

Balanced Efficiency Profile Ranking Overall

rank team run balanced efficiency profile rank rank impresso profile score rank hipe parameter count rank hipe model size mean impresso profile score hipe parameter count hipe model size mb
1 team14 run3 11.75 15 8 9 0.6782 277730309 1111
2 team12 run2 13 3 22 24 0.8156 5123178979 9600
3 team12 run1 13.5 4 22 24 0.8148 5123178979 9600
4 team2 run1 14.25 24 5 4 0.6065 2087375 87
5 team14 run1 14.75 18 12 11 0.6653 466577920 1780
6 team15 run2 15 29 1 1 0.5664 0 0
7 baseline run1 15.25 14 19 14 0.6818 3000000000 2147.023
8 team11 run2 15.5 9 21 23 0.739 4465470464 9012
8 team13 run1 15.5 1 30 30 0.8419 116830000000 65238
8 team3 run3 15.5 13 20 16 0.6864 4000000000 2840
9 team2 run2 15.75 27 5 4 0.5819 2087375 87
10 team13 run3 16 2 30 30 0.8369 116830000000 65238
11 team1 run2 16.25 19 14 13 0.6558 560965127 2140
12 team5 run2 16.5 12 20 22 0.7052 4000000000 7600
13 team17 run2 17.25 26 9 8 0.5853 278043651 1061
14 team13 run2 17.5 5 30 30 0.7998 116830000000 65238
15 team2 run3 17.75 31 5 4 0.5562 2087375 87
16 team11 run1 18.25 11 25 26 0.7198 9300029952 18398
17 team7 run3 18.75 34 4 3 0.5484 12399 0.81
18 team17 run1 19 8 29 31 0.7629 101927226758 195716
19 team1 run3 19.25 6 32 33 0.7925 999999999999 999999
20 team7 run1 19.5 37 2 2 0.5338 12279 0.8
20 team7 run2 19.5 36 3 3 0.5374 12365 0.81
21 team1 run1 19.75 7 32 33 0.7862 999999999999 999999
22 team9 run1 20 20 19 21 0.6539 3000000000 6248
23 team11 run3 20.25 23 17 18 0.6145 1949101888 3845
23 team3 run1 20.25 25 16 15 0.6005 1500000000 2340
23 team6 run2 20.25 30 11 10 0.5633 355000000 1424
23 team9 run2 20.25 16 24 25 0.6765 7000000000 15300
24 team9 run3 20.75 10 31 32 0.7284 120000000000 240000
25 team6 run1 21.25 32 11 10 0.5544 355000000 1424
26 team3 run2 21.75 22 23 20 0.6259 5900000000 5980
27 random run1 22 43 1 1 0.4913 0 0
27 team17 run3 22 28 15 17 0.576 838778678 3217
28 team10 run2 22.75 17 28 29 0.6721 27000000000 54000
28 team15 run1 22.75 40 6 5 0.5215 208935168 816
28 team5 run1 22.75 39 7 6 0.5245 270000000 1030
29 team10 run3 23.75 21 26 27 0.6274 24000000000 48000
30 team4 run1 25.25 42 10 7 0.4988 278054405 1060
31 team15 run3 25.75 33 18 19 0.5493 2274069824 4442
32 team14 run2 26.75 41 13 12 0.5155 466585989 1866
33 team5 run3 28 35 20 22 0.5426 4000000000 7600
34 team10 run1 32.75 38 27 28 0.5252 26000000000 52000

Top 3 teams by best run:

  1. MILRIT (team14), run3, table rank 1, balanced efficiency profile rank 11.75
  2. whereami (team12), run2, table rank 2, balanced efficiency profile rank 13
  3. DS@GT_HIPE (team2), run1, table rank 4, balanced efficiency profile rank 14.25

This is an additional analysis ranking. It is not the guideline-defined Efficiency Profile Ranking; it gives equal total weight to accuracy and to the combined resource ranks.

Efficiency Profile Ranking German

rank team run submission mean efficiency profile rank rank impresso profile score rank hipe parameter count rank hipe model size impresso profile score hipe parameter count hipe model size mb diagnostics
1 team14 run3 team14_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 10 13 8 9 0.692 277730309 1111 Comparison / Metrics
1 team7 run1 team7_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 10 26 2 2 0.6094 12279 0.8 Comparison / Metrics
1 team7 run3 team7_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 10 23 4 3 0.6158 12399 0.81 Comparison / Metrics
2 team2 run1 team2_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 11 24 5 4 0.6139 2087375 87 Comparison / Metrics
2 team7 run2 team7_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 11 27 3 3 0.6031 12365 0.81 Comparison / Metrics
3 team15 run2 team15_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 11.6667 33 1 1 0.5598 0 0 Comparison / Metrics
4 team14 run1 team14_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 12.3333 14 12 11 0.6885 466577920 1780 Comparison / Metrics
4 team2 run2 team2_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 12.3333 28 5 4 0.592 2087375 87 Comparison / Metrics
5 team2 run3 team2_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 13.3333 31 5 4 0.5782 2087375 87 Comparison / Metrics
6 random run1 random_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 15 43 1 1 0.4783 0 0 Comparison / Metrics
7 team1 run2 team1_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 15.3333 19 14 13 0.6455 560965127 2140 Comparison / Metrics
8 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 16.3333 16 19 14 0.6578 3000000000 2147.023 Comparison / Metrics
8 team12 run1 team12_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 16.3333 3 22 24 0.8508 5123178979 9600 Comparison / Metrics
8 team15 run1 team15_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 16.3333 38 6 5 0.532 208935168 816 Comparison / Metrics
8 team17 run2 team17_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 16.3333 32 9 8 0.5707 278043651 1061 Comparison / Metrics
9 team12 run2 team12_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 16.6667 4 22 24 0.8472 5123178979 9600 Comparison / Metrics
9 team6 run2 team6_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 16.6667 29 11 10 0.5885 355000000 1424 Comparison / Metrics
10 team3 run3 team3_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 17 15 20 16 0.6621 4000000000 2840 Comparison / Metrics
10 team5 run2 team5_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 17 9 20 22 0.7562 4000000000 7600 Comparison / Metrics
11 team11 run2 team11_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 18 10 21 23 0.7345 4465470464 9012 Comparison / Metrics
11 team5 run1 team5_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 18 41 7 6 0.5 270000000 1030 Comparison / Metrics
12 team6 run1 team6_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 18.6667 35 11 10 0.5503 355000000 1424 Comparison / Metrics
13 team11 run3 team11_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 19 22 17 18 0.6192 1949101888 3845 Comparison / Metrics
13 team9 run1 team9_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 19 17 19 21 0.655 3000000000 6248 Comparison / Metrics
14 team4 run1 team4_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 19.6667 42 10 7 0.4906 278054405 1060 Comparison / Metrics
15 team13 run3 team13_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 20.3333 1 30 30 0.8721 116830000000 65238 Comparison / Metrics
15 team3 run1 team3_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 20.3333 30 16 15 0.5795 1500000000 2340 Comparison / Metrics
16 team11 run1 team11_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 20.6667 11 25 26 0.7216 9300029952 18398 Comparison / Metrics
16 team13 run1 team13_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 20.6667 2 30 30 0.8599 116830000000 65238 Comparison / Metrics
17 team14 run2 team14_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 21.6667 40 13 12 0.5167 466585989 1866 Comparison / Metrics
17 team17 run1 team17_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 21.6667 5 29 31 0.8209 101927226758 195716 Comparison / Metrics
18 team9 run2 team9_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 22.3333 18 24 25 0.646 7000000000 15300 Comparison / Metrics
19 team13 run2 team13_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 22.6667 8 30 30 0.7866 116830000000 65238 Comparison / Metrics
19 team17 run3 team17_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 22.6667 36 15 17 0.549 838778678 3217 Comparison / Metrics
19 team3 run2 team3_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 22.6667 25 23 20 0.6102 5900000000 5980 Comparison / Metrics
20 team1 run1 team1_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 23.6667 6 32 33 0.8088 999999999999 999999 Comparison / Metrics
21 team1 run3 team1_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 24 7 32 33 0.8071 999999999999 999999 Comparison / Metrics
22 team10 run3 team10_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 24.3333 20 26 27 0.6381 24000000000 48000 Comparison / Metrics
23 team9 run3 team9_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 25 12 31 32 0.7166 120000000000 240000 Comparison / Metrics
24 team15 run3 team15_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 25.3333 39 18 19 0.5187 2274069824 4442 Comparison / Metrics
24 team5 run3 team5_HIPE-2026-v1.0-impresso-test-de_run3.jsonl 25.3333 34 20 22 0.553 4000000000 7600 Comparison / Metrics
25 team10 run2 team10_HIPE-2026-v1.0-impresso-test-de_run2.jsonl 26 21 28 29 0.6231 27000000000 54000 Comparison / Metrics
26 team10 run1 team10_HIPE-2026-v1.0-impresso-test-de_run1.jsonl 30.6667 37 27 28 0.5329 26000000000 52000 Comparison / Metrics

Top 3 teams by best run:

  1. MILRIT (team14), run3, table rank 1, mean efficiency profile rank 10
  2. ROSTI (team7), run1, table rank 1, mean efficiency profile rank 10
  3. DS@GT_HIPE (team2), run1, table rank 2, mean efficiency profile rank 11

Efficiency Profile Ranking English

rank team run submission mean efficiency profile rank rank impresso profile score rank hipe parameter count rank hipe model size impresso profile score hipe parameter count hipe model size mb diagnostics
1 team15 run2 team15_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 10.3333 29 1 1 0.5529 0 0 Comparison / Metrics
2 team2 run1 team2_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 11.3333 24 6 4 0.6044 2087375 87 Comparison / Metrics
3 team14 run3 team14_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 12.6667 19 9 10 0.6351 277730309 1111 Comparison / Metrics
3 team2 run3 team2_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 12.6667 28 6 4 0.5673 2087375 87 Comparison / Metrics
4 team17 run2 team17_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 13.3333 21 10 9 0.6247 278043651 1061 Comparison / Metrics
5 team7 run3 team7_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 14.3333 35 5 3 0.5307 12399 0.81 Comparison / Metrics
6 team2 run2 team2_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 14.6667 34 6 4 0.5317 2087375 87 Comparison / Metrics
6 team7 run2 team7_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 14.6667 37 4 3 0.518 12365 0.81 Comparison / Metrics
7 random run1 random_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 15.3333 44 1 1 0.462 0 0 Comparison / Metrics
7 team7 run1 team7_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 15.3333 41 3 2 0.5042 12279 0.8 Comparison / Metrics
8 team3 run1 team3_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 15.6667 14 17 16 0.6786 1500000000 2340 Comparison / Metrics
8 team5 run1 team5_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 15.6667 32 8 7 0.5445 270000000 1030 Comparison / Metrics
9 team12 run2 team12_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 16.3333 1 23 25 0.8058 5123178979 9600 Comparison / Metrics
10 team16 run1 team16_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 16.6667 43 2 5 0.4939 110 433 Comparison / Metrics
10 team3 run3 team3_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 16.6667 12 21 17 0.6841 4000000000 2840 Comparison / Metrics
11 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 17 16 20 15 0.6638 3000000000 2147.023 Comparison / Metrics
11 team15 run1 team15_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 17 38 7 6 0.518 208935168 816 Comparison / Metrics
12 team12 run1 team12_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 17.3333 4 23 25 0.7982 5123178979 9600 Comparison / Metrics
12 team14 run1 team14_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 17.3333 27 13 12 0.5756 466577920 1780 Comparison / Metrics
13 team6 run1 team6_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 17.6667 30 12 11 0.5511 355000000 1424 Comparison / Metrics
14 team6 run2 team6_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 18 31 12 11 0.5451 355000000 1424 Comparison / Metrics
15 team1 run2 team1_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 18.3333 26 15 14 0.5889 560965127 2140 Comparison / Metrics
15 team11 run2 team11_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 18.3333 9 22 24 0.7119 4465470464 9012 Comparison / Metrics
16 team17 run3 team17_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 19 23 16 18 0.613 838778678 3217 Comparison / Metrics
16 team9 run1 team9_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 19 15 20 22 0.6645 3000000000 6248 Comparison / Metrics
17 team11 run3 team11_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 19.6667 22 18 19 0.6209 1949101888 3845 Comparison / Metrics
18 team4 run1 team4_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 20.3333 42 11 8 0.497 278054405 1060 Comparison / Metrics
19 team3 run2 team3_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 20.6667 17 24 21 0.6566 5900000000 5980 Comparison / Metrics
20 team14 run2 team14_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 21 36 14 13 0.5267 466585989 1866 Comparison / Metrics
21 team11 run1 team11_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 21.3333 11 26 27 0.696 9300029952 18398 Comparison / Metrics
21 team13 run1 team13_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 21.3333 2 31 31 0.803 116830000000 65238 Comparison / Metrics
21 team5 run2 team5_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 21.3333 20 21 23 0.6315 4000000000 7600 Comparison / Metrics
21 team9 run2 team9_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 21.3333 13 25 26 0.6803 7000000000 15300 Comparison / Metrics
22 team13 run3 team13_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 21.6667 3 31 31 0.8016 116830000000 65238 Comparison / Metrics
23 team13 run2 team13_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 22.3333 5 31 31 0.7605 116830000000 65238 Comparison / Metrics
24 team17 run1 team17_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 24 10 30 32 0.7031 101927226758 195716 Comparison / Metrics
24 team9 run3 team9_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 24 7 32 33 0.7279 120000000000 240000 Comparison / Metrics
25 team1 run3 team1_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 24.3333 6 33 34 0.7471 999999999999 999999 Comparison / Metrics
26 team1 run1 team1_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 25 8 33 34 0.7138 999999999999 999999 Comparison / Metrics
27 team10 run2 team10_HIPE-2026-v1.0-impresso-test-en_run2.jsonl 25.6667 18 29 30 0.6524 27000000000 54000 Comparison / Metrics
28 team15 run3 team15_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 26.3333 40 19 20 0.5126 2274069824 4442 Comparison / Metrics
29 team10 run3 team10_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 26.6667 25 27 28 0.5904 24000000000 48000 Comparison / Metrics
30 team5 run3 team5_HIPE-2026-v1.0-impresso-test-en_run3.jsonl 27.6667 39 21 23 0.5143 4000000000 7600 Comparison / Metrics
31 team10 run1 team10_HIPE-2026-v1.0-impresso-test-en_run1.jsonl 30 33 28 29 0.5382 26000000000 52000 Comparison / Metrics

Top 3 teams by best run:

  1. FI-CODE (team15), run2, table rank 1, mean efficiency profile rank 10.3333
  2. DS@GT_HIPE (team2), run1, table rank 2, mean efficiency profile rank 11.3333
  3. MILRIT (team14), run3, table rank 3, mean efficiency profile rank 12.6667

Efficiency Profile Ranking French

rank team run submission mean efficiency profile rank rank impresso profile score rank hipe parameter count rank hipe model size impresso profile score hipe parameter count hipe model size mb diagnostics
1 team15 run2 team15_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 9.6667 27 1 1 0.5865 0 0 Comparison / Metrics
2 team2 run2 team2_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 10.3333 22 5 4 0.6219 2087375 87 Comparison / Metrics
3 team14 run3 team14_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 11.6667 18 8 9 0.7074 277730309 1111 Comparison / Metrics
3 team2 run1 team2_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 11.6667 26 5 4 0.6012 2087375 87 Comparison / Metrics
4 random run1 random_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 12 34 1 1 0.5334 0 0 Comparison / Metrics
5 team14 run1 team14_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 12.3333 14 12 11 0.7318 466577920 1780 Comparison / Metrics
6 team1 run2 team1_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 13.3333 13 14 13 0.7329 560965127 2140 Comparison / Metrics
7 team2 run3 team2_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 15 36 5 4 0.5231 2087375 87 Comparison / Metrics
8 team17 run2 team17_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 15.6667 30 9 8 0.5606 278043651 1061 Comparison / Metrics
8 team7 run1 team7_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 15.6667 43 2 2 0.4877 12279 0.8 Comparison / Metrics
9 team15 run1 team15_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 16 37 6 5 0.5144 208935168 816 Comparison / Metrics
9 team5 run1 team5_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 16 35 7 6 0.529 270000000 1030 Comparison / Metrics
9 team7 run2 team7_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 16 42 3 3 0.491 12365 0.81 Comparison / Metrics
9 team7 run3 team7_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 16 41 4 3 0.4987 12399 0.81 Comparison / Metrics
10 baseline run1 baseline_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 16.3333 16 19 14 0.7239 3000000000 2147.023 Comparison / Metrics
11 team6 run1 team6_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 16.6667 29 11 10 0.5619 355000000 1424 Comparison / Metrics
12 team11 run2 team11_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 17.3333 8 21 23 0.7706 4465470464 9012 Comparison / Metrics
12 team12 run1 team12_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 17.3333 6 22 24 0.7955 5123178979 9600 Comparison / Metrics
13 team12 run2 team12_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 17.6667 7 22 24 0.7939 5123178979 9600 Comparison / Metrics
13 team3 run3 team3_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 17.6667 17 20 16 0.713 4000000000 2840 Comparison / Metrics
13 team6 run2 team6_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 17.6667 32 11 10 0.5564 355000000 1424 Comparison / Metrics
14 team4 run1 team4_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 18.3333 38 10 7 0.5088 278054405 1060 Comparison / Metrics
15 team5 run2 team5_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 19 15 20 22 0.7278 4000000000 7600 Comparison / Metrics
16 team11 run3 team11_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 20 25 17 18 0.6033 1949101888 3845 Comparison / Metrics
16 team15 run3 team15_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 20 23 18 19 0.6165 2274069824 4442 Comparison / Metrics
16 team17 run3 team17_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 20 28 15 17 0.5658 838778678 3217 Comparison / Metrics
17 team11 run1 team11_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 20.3333 10 25 26 0.7418 9300029952 18398 Comparison / Metrics
17 team13 run1 team13_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 20.3333 1 30 30 0.8628 116830000000 65238 Comparison / Metrics
17 team9 run1 team9_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 20.3333 21 19 21 0.642 3000000000 6248 Comparison / Metrics
18 team13 run2 team13_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 20.6667 2 30 30 0.8523 116830000000 65238 Comparison / Metrics
19 team13 run3 team13_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 21 3 30 30 0.837 116830000000 65238 Comparison / Metrics
20 team3 run1 team3_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 21.3333 33 16 15 0.5433 1500000000 2340 Comparison / Metrics
21 team14 run2 team14_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 21.6667 40 13 12 0.5031 466585989 1866 Comparison / Metrics
22 team3 run2 team3_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 22.3333 24 23 20 0.611 5900000000 5980 Comparison / Metrics
23 team10 run2 team10_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 22.6667 11 28 29 0.7409 27000000000 54000 Comparison / Metrics
23 team9 run2 team9_HIPE-2026-v1.0-impresso-test-fr_run2.jsonl 22.6667 19 24 25 0.7033 7000000000 15300 Comparison / Metrics
24 team1 run1 team1_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 23 4 32 33 0.836 999999999999 999999 Comparison / Metrics
24 team17 run1 team17_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 23 9 29 31 0.7648 101927226758 195716 Comparison / Metrics
25 team1 run3 team1_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 23.3333 5 32 33 0.8232 999999999999 999999 Comparison / Metrics
26 team10 run3 team10_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 24.3333 20 26 27 0.6538 24000000000 48000 Comparison / Metrics
26 team5 run3 team5_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 24.3333 31 20 22 0.5605 4000000000 7600 Comparison / Metrics
27 team9 run3 team9_HIPE-2026-v1.0-impresso-test-fr_run3.jsonl 25 12 31 32 0.7409 120000000000 240000 Comparison / Metrics
28 team10 run1 team10_HIPE-2026-v1.0-impresso-test-fr_run1.jsonl 31.3333 39 27 28 0.5044 26000000000 52000 Comparison / Metrics

Top 3 teams by best run:

  1. FI-CODE (team15), run2, table rank 1, mean efficiency profile rank 9.6667
  2. DS@GT_HIPE (team2), run2, table rank 2, mean efficiency profile rank 10.3333
  3. MILRIT (team14), run3, table rank 3, mean efficiency profile rank 11.6667