Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4,965 changes: 4,965 additions & 0 deletions data/annex_c_third_place.json

Large diffs are not rendered by default.

125 changes: 68 additions & 57 deletions data/leaderboard.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"last_updated": "2026-06-30T19:44:42.498795+00:00",
"total_results": 76,
"last_updated": "2026-06-30T19:57:44.920389+00:00",
"total_results": 77,
"total_models": 11,
"qualifiers_known": 32,
"qualifiers_ready": true,
Expand All @@ -10,12 +10,12 @@
"model": "MiMo-V2.5-Pro",
"model_id": "xiaomi/mimo-v2.5-pro-20260422",
"brier_group": 35.0096,
"brier_knockout": 0.9257,
"brier_total": 16.632216,
"brier_knockout": 1.4441,
"brier_total": 16.461897,
"quiniela_points": 52,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 26,
"score": 0.8125,
Expand Down Expand Up @@ -47,10 +47,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"CAN",
"MAR"
"MAR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -136,12 +137,12 @@
"model": "DeepSeek-V4-Pro",
"model_id": "deepseek/deepseek-v4-pro-20260423",
"brier_group": 35.0214,
"brier_knockout": 1.065,
"brier_total": 16.645137,
"brier_knockout": 1.555,
"brier_total": 16.474616,
"quiniela_points": 48,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -171,10 +172,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -260,12 +262,12 @@
"model": "Nex-N2-Pro",
"model_id": "nex-agi/nex-n2-pro:free",
"brier_group": 35.1942,
"brier_knockout": 0.8793,
"brier_total": 16.717216,
"brier_knockout": 1.1709,
"brier_total": 16.530464,
"quiniela_points": 47,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -295,11 +297,12 @@
"hits": 1,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"CAN",
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -386,12 +389,12 @@
"model": "MiniMax-M3",
"model_id": "minimax/minimax-m3-20260531",
"brier_group": 35.3422,
"brier_knockout": 0.8113,
"brier_total": 16.783742,
"brier_knockout": 1.4837,
"brier_total": 16.61997,
"quiniela_points": 53,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -421,9 +424,10 @@
"hits": 3,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR"
"MAR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -508,12 +512,12 @@
"model": "Gemini-3.5-Flash",
"model_id": "google/gemini-3.5-flash-20260519",
"brier_group": 35.535,
"brier_knockout": 0.825,
"brier_total": 16.875789,
"brier_knockout": 1.2475,
"brier_total": 16.694773,
"quiniela_points": 51,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 26,
"score": 0.8125,
Expand Down Expand Up @@ -545,9 +549,10 @@
"hits": 3,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR"
"MAR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -632,12 +637,12 @@
"model": "Qwen-3.7-Max",
"model_id": "qwen/qwen3.7-max-20260520",
"brier_group": 35.735,
"brier_knockout": 1.2075,
"brier_total": 16.990658,
"brier_knockout": 1.77,
"brier_total": 16.822208,
"quiniela_points": 46,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -667,11 +672,12 @@
"hits": 1,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"CAN",
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -758,12 +764,12 @@
"model": "GPT-5.5",
"model_id": "openai/gpt-5.5-20260423",
"brier_group": 35.8112,
"brier_knockout": 0.9222,
"brier_total": 17.011737,
"brier_knockout": 1.3066,
"brier_total": 16.827743,
"quiniela_points": 47,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -793,10 +799,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -882,12 +889,12 @@
"model": "Grok-4.3",
"model_id": "x-ai/grok-4.3-20260430",
"brier_group": 35.909,
"brier_knockout": 1.2217,
"brier_total": 17.073826,
"brier_knockout": 1.8301,
"brier_total": 16.907461,
"quiniela_points": 47,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 25,
"score": 0.78125,
Expand Down Expand Up @@ -921,10 +928,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -1010,12 +1018,12 @@
"model": "Kimi-K2.6",
"model_id": "moonshotai/kimi-k2.6-20260420",
"brier_group": 36.1986,
"brier_knockout": 1.0554,
"brier_total": 17.202253,
"brier_knockout": 1.6954,
"brier_total": 17.034112,
"quiniela_points": 45,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 26,
"score": 0.8125,
Expand Down Expand Up @@ -1047,10 +1055,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -1136,12 +1145,12 @@
"model": "Claude-Fable-5",
"model_id": "anthropic/claude-5-fable-20260609",
"brier_group": 36.638,
"brier_knockout": 0.8639,
"brier_total": 17.400311,
"brier_knockout": 1.4264,
"brier_total": 17.222078,
"quiniela_points": 48,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 27,
"score": 0.84375,
Expand Down Expand Up @@ -1171,9 +1180,10 @@
"hits": 3,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR"
"MAR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down Expand Up @@ -1258,12 +1268,12 @@
"model": "GLM-5.1",
"model_id": "z-ai/glm-5.1-20260406",
"brier_group": 36.7908,
"brier_knockout": 0.945,
"brier_total": 17.476958,
"brier_knockout": 1.3675,
"brier_total": 17.289692,
"quiniela_points": 50,
"roi": null,
"roi_status": "no_market_data",
"n_matches_scored": 76,
"n_matches_scored": 77,
"qualifier_accuracy": {
"hits": 26,
"score": 0.8125,
Expand Down Expand Up @@ -1295,10 +1305,11 @@
"hits": 2,
"total": 16,
"predicted_count": 16,
"reached_count": 4,
"reached_count": 5,
"missed": [
"MAR",
"NOR"
"NOR",
"PAR"
],
"false_positives": [
"ARG",
Expand Down
7 changes: 4 additions & 3 deletions data/results/2026-06-29.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"date": "2026-06-29",
"last_updated": "2026-06-30T19:44:42.427075+00:00",
"last_updated": "2026-06-30T19:54:38.098376+00:00",
"matches": [
{
"fd_id": null,
Expand All @@ -18,7 +18,7 @@
},
{
"fd_id": null,
"match_id": null,
"match_id": 74,
"home_team": "GER",
"away_team": "PAR",
"score": {
Expand All @@ -28,7 +28,8 @@
"outcome": "away",
"date": "2026-06-29",
"stage": "R32",
"group": null
"group": null,
"round": "round_of_32"
},
{
"fd_id": null,
Expand Down
Loading
Loading