Results & Logs

Official Results (Awards)

The list of awarded teams is being compiled.

Awards will be announced at the AIWolfDial 2026 workshop (October 17–21, 2026, INLG 2026, Utrecht).

Win Rates

Computed from the logs of all games that finished normally in the main competition. The official win rate is "Adjusted": the per-role win rates averaged with the weights of the village's role composition, so that uneven role assignments cancel out; teams are ranked by it. "Overall" is simply wins divided by games, and per-role cells show the win rate in that role with (wins / games).

Round 1, 5-player village (220 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Possessed	Werewolf
1	yharada	100	61.0%	61.0%	70.0% (28/40)	75.0% (15/20)	25.0% (5/20)	65.0% (13/20)
2	Oxymoron	100	61.0%	61.0%	72.5% (29/40)	75.0% (15/20)	40.0% (8/20)	45.0% (9/20)
3	noisy_watcher	100	60.0%	60.0%	77.5% (31/40)	70.0% (14/20)	40.0% (8/20)	35.0% (7/20)
4	SunameLLi	100	57.0%	57.0%	67.5% (27/40)	65.0% (13/20)	30.0% (6/20)	55.0% (11/20)
5	wool_100%	100	57.0%	57.0%	62.5% (25/40)	70.0% (14/20)	60.0% (12/20)	30.0% (6/20)
6	ryanleeai	100	56.0%	56.0%	75.0% (30/40)	60.0% (12/20)	35.0% (7/20)	35.0% (7/20)
7	yshimoda	100	51.0%	51.0%	50.0% (20/40)	80.0% (16/20)	30.0% (6/20)	45.0% (9/20)
8	kataken14f	100	49.0%	49.0%	62.5% (25/40)	60.0% (12/20)	40.0% (8/20)	20.0% (4/20)
9	CamelliaDragons	100	45.0%	45.0%	57.5% (23/40)	65.0% (13/20)	20.0% (4/20)	25.0% (5/20)
10	gotsumori-NLP	100	43.0%	43.0%	62.5% (25/40)	15.0% (3/20)	45.0% (9/20)	30.0% (6/20)
11	CanisLupus	100	40.0%	40.0%	42.5% (17/40)	65.0% (13/20)	35.0% (7/20)	15.0% (3/20)

Round 1, 9-player village (18 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Bodyguard	Medium	Possessed	Werewolf
1	CamelliaDragons	18	66.7%	66.7%	83.3% (5/6)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	75.0% (3/4)
2	CanisLupus	18	66.7%	66.7%	83.3% (5/6)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	100.0% (2/2)	50.0% (2/4)
3	Oxymoron	18	66.7%	66.7%	50.0% (3/6)	50.0% (1/2)	100.0% (2/2)	100.0% (2/2)	50.0% (1/2)	75.0% (3/4)
4	wool_100%	18	55.6%	55.6%	66.7% (4/6)	0.0% (0/2)	50.0% (1/2)	100.0% (2/2)	100.0% (2/2)	25.0% (1/4)
5	yshimoda	18	55.6%	55.6%	50.0% (3/6)	50.0% (1/2)	100.0% (2/2)	50.0% (1/2)	50.0% (1/2)	50.0% (2/4)
6	ryanleeai	18	44.4%	44.4%	33.3% (2/6)	100.0% (2/2)	50.0% (1/2)	50.0% (1/2)	0.0% (0/2)	50.0% (2/4)
7	noisy_watcher	18	44.4%	44.4%	50.0% (3/6)	50.0% (1/2)	0.0% (0/2)	100.0% (2/2)	50.0% (1/2)	25.0% (1/4)
8	SunameLLi	18	33.3%	33.3%	33.3% (2/6)	50.0% (1/2)	100.0% (2/2)	0.0% (0/2)	0.0% (0/2)	25.0% (1/4)
9	yharada	18	33.3%	33.3%	50.0% (3/6)	100.0% (2/2)	0.0% (0/2)	0.0% (0/2)	0.0% (0/2)	25.0% (1/4)

Round 1, Speak-Anytime Track, 5-player village (14 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Possessed	Werewolf
1	yharada	10	60.0%	60.0%	25.0% (1/4)	100.0% (2/2)	50.0% (1/2)	100.0% (2/2)
2	CanisLupus	10	60.0%	60.0%	75.0% (3/4)	0.0% (0/2)	100.0% (2/2)	50.0% (1/2)
3	Oxymoron	10	50.0%	50.0%	50.0% (2/4)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)
4	CamelliaDragons	10	50.0%	50.0%	50.0% (2/4)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)
5	wool_100%	10	50.0%	50.0%	25.0% (1/4)	100.0% (2/2)	100.0% (2/2)	0.0% (0/2)
6	noisy_watcher	10	40.0%	40.0%	50.0% (2/4)	50.0% (1/2)	0.0% (0/2)	50.0% (1/2)
7	SunameLLi	10	40.0%	40.0%	75.0% (3/4)	0.0% (0/2)	0.0% (0/2)	50.0% (1/2)

Round 2, 5-player village (270 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Possessed	Werewolf
1	yatolab	75	69.3%	69.3%	76.7% (23/30)	53.3% (8/15)	73.3% (11/15)	66.7% (10/15)
2	AGKAI	75	60.0%	60.0%	66.7% (20/30)	46.7% (7/15)	66.7% (10/15)	53.3% (8/15)
3	wool_100%	75	58.7%	58.7%	53.3% (16/30)	80.0% (12/15)	46.7% (7/15)	60.0% (9/15)
4	CanisLupus	75	57.3%	57.3%	66.7% (20/30)	66.7% (10/15)	60.0% (9/15)	26.7% (4/15)
5	yharada	75	56.0%	56.0%	56.7% (17/30)	60.0% (9/15)	40.0% (6/15)	66.7% (10/15)
6	NTT-HAI	75	54.7%	54.7%	46.7% (14/30)	60.0% (9/15)	60.0% (9/15)	60.0% (9/15)
7	ryanleeai	75	54.7%	54.7%	40.0% (12/30)	86.7% (13/15)	40.0% (6/15)	66.7% (10/15)
8	SunameLLi	75	52.0%	52.0%	66.7% (20/30)	53.3% (8/15)	40.0% (6/15)	33.3% (5/15)
9	CamelliaDragons	75	50.7%	50.7%	60.0% (18/30)	40.0% (6/15)	46.7% (7/15)	46.7% (7/15)
10	kataken14f	75	50.7%	50.7%	53.3% (16/30)	80.0% (12/15)	33.3% (5/15)	33.3% (5/15)
11	UEC-IL	75	50.7%	50.7%	53.3% (16/30)	60.0% (9/15)	40.0% (6/15)	46.7% (7/15)
12	Luna	75	50.7%	50.7%	53.3% (16/30)	53.3% (8/15)	40.0% (6/15)	53.3% (8/15)
13	carrot	75	46.7%	46.7%	50.0% (15/30)	53.3% (8/15)	26.7% (4/15)	53.3% (8/15)
14	noisy_watcher	75	45.3%	45.3%	63.3% (19/30)	46.7% (7/15)	26.7% (4/15)	26.7% (4/15)
15	Mackerel	75	41.3%	41.3%	46.7% (14/30)	53.3% (8/15)	40.0% (6/15)	20.0% (3/15)
16	yshimoda	75	41.3%	41.3%	50.0% (15/30)	40.0% (6/15)	40.0% (6/15)	26.7% (4/15)
17	Oxymoron	75	41.3%	41.3%	50.0% (15/30)	40.0% (6/15)	26.7% (4/15)	40.0% (6/15)
18	gotsumori-NLP	75	38.7%	38.7%	46.7% (14/30)	26.7% (4/15)	53.3% (8/15)	20.0% (3/15)

Round 2, 9-player village (28 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Bodyguard	Medium	Possessed	Werewolf
1	yharada	18	66.7%	66.7%	83.3% (5/6)	50.0% (1/2)	100.0% (2/2)	50.0% (1/2)	50.0% (1/2)	50.0% (2/4)
2	ryanleeai	18	61.1%	61.1%	50.0% (3/6)	50.0% (1/2)	50.0% (1/2)	100.0% (2/2)	0.0% (0/2)	100.0% (4/4)
3	kataken14f	18	61.1%	61.1%	50.0% (3/6)	100.0% (2/2)	50.0% (1/2)	100.0% (2/2)	50.0% (1/2)	50.0% (2/4)
4	SunameLLi	18	61.1%	61.1%	33.3% (2/6)	100.0% (2/2)	100.0% (2/2)	100.0% (2/2)	100.0% (2/2)	25.0% (1/4)
5	UEC-IL	18	61.1%	61.1%	66.7% (4/6)	50.0% (1/2)	100.0% (2/2)	50.0% (1/2)	50.0% (1/2)	50.0% (2/4)
6	noisy_watcher	18	55.6%	55.6%	83.3% (5/6)	50.0% (1/2)	0.0% (0/2)	50.0% (1/2)	50.0% (1/2)	50.0% (2/4)
7	wool_100%	18	55.6%	55.6%	50.0% (3/6)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	100.0% (2/2)	50.0% (2/4)
8	Oxymoron	18	50.0%	50.0%	66.7% (4/6)	100.0% (2/2)	0.0% (0/2)	50.0% (1/2)	50.0% (1/2)	25.0% (1/4)
9	Mackerel	18	50.0%	50.0%	16.7% (1/6)	100.0% (2/2)	100.0% (2/2)	100.0% (2/2)	50.0% (1/2)	25.0% (1/4)
10	CanisLupus	18	44.4%	44.4%	50.0% (3/6)	0.0% (0/2)	100.0% (2/2)	50.0% (1/2)	0.0% (0/2)	50.0% (2/4)
11	yatolab	18	44.4%	44.4%	66.7% (4/6)	0.0% (0/2)	50.0% (1/2)	50.0% (1/2)	0.0% (0/2)	50.0% (2/4)
12	yshimoda	18	44.4%	44.4%	83.3% (5/6)	0.0% (0/2)	50.0% (1/2)	0.0% (0/2)	50.0% (1/2)	25.0% (1/4)
13	CamelliaDragons	18	44.4%	44.4%	66.7% (4/6)	100.0% (2/2)	0.0% (0/2)	0.0% (0/2)	0.0% (0/2)	50.0% (2/4)
14	carrot	18	33.3%	33.3%	33.3% (2/6)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)	0.0% (0/4)

Round 2, Speak-Anytime Track, 5-player village (24 games)

#	Team	Games	Adjusted	Overall	Villager	Seer	Possessed	Werewolf
1	yatolab	10	70.0%	70.0%	75.0% (3/4)	100.0% (2/2)	100.0% (2/2)	0.0% (0/2)
2	ryanleeai	10	70.0%	70.0%	100.0% (4/4)	0.0% (0/2)	100.0% (2/2)	50.0% (1/2)
3	wool_100%	10	60.0%	60.0%	75.0% (3/4)	100.0% (2/2)	50.0% (1/2)	0.0% (0/2)
4	SunameLLi	10	60.0%	60.0%	75.0% (3/4)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)
5	noisy_watcher	10	60.0%	60.0%	75.0% (3/4)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)
6	Oxymoron	10	50.0%	50.0%	50.0% (2/4)	100.0% (2/2)	0.0% (0/2)	50.0% (1/2)
7	yharada	10	50.0%	50.0%	50.0% (2/4)	50.0% (1/2)	0.0% (0/2)	100.0% (2/2)
8	kanolab	10	50.0%	50.0%	50.0% (2/4)	50.0% (1/2)	50.0% (1/2)	50.0% (1/2)
9	kataken14f	10	40.0%	40.0%	50.0% (2/4)	0.0% (0/2)	0.0% (0/2)	100.0% (2/2)
10	CanisLupus	10	40.0%	40.0%	25.0% (1/4)	100.0% (2/2)	50.0% (1/2)	0.0% (0/2)
11	UEC-IL	10	40.0%	40.0%	50.0% (2/4)	50.0% (1/2)	50.0% (1/2)	0.0% (0/2)
12	CamelliaDragons	10	30.0%	30.0%	25.0% (1/4)	50.0% (1/2)	0.0% (0/2)	50.0% (1/2)

Game Metrics

Behavioural metrics computed mechanically from the game logs, independent of dialogue quality. Each value is a ratio against what random play would produce (1.00 = random). "Executed", "divined" and "guarded" show how often the team was targeted relative to chance; lower is better for being executed or divined. "Divination accuracy" and "vote accuracy" show how often the team found a werewolf relative to chance; higher is better. "Possessed avoidance" is the rate at which, as the possessed, the team voted for someone other than a werewolf.

Round 1, 5-player village

Team	Executed	Divined	Divination accuracy	Vote accuracy	Possessed avoidance
yharada	0.32	0.86	1.43	1.47	0.40
Oxymoron	0.86	0.89	1.23	1.58	0.69
noisy_watcher	0.79	1.01	0.84	1.58	0.75
SunameLLi	0.93	0.84	1.00	1.39	0.70
wool_100%	1.07	1.22	1.22	1.34	0.67
ryanleeai	0.93	0.87	1.04	1.39	0.48
yshimoda	1.00	0.88	1.30	1.48	0.67
CamelliaDragons	0.94	1.33	1.64	1.64	0.80
gotsumori-NLP	1.51	1.65	0.97	0.99	0.73
CanisLupus	1.46	0.62	0.68	1.09	0.70
kataken	1.26	0.85	1.71	1.64	0.68

Round 1, 9-player village

Team	Executed	Divined	Guarded	Divination accuracy	Vote accuracy	Possessed avoidance
CamelliaDragons	0.33	1.86	1.34	1.08	1.20	0.67
CanisLupus	1.93	1.13	2.59	1.52	1.84	0.75
Oxymoron	1.04	0.42	0.34	0.68	1.67	0.75
wool_100%	1.28	1.03	1.53	1.27	1.77	1.00
yshimoda	1.08	0.53	0.57	-	1.70	0.25
ryanleeai	0.74	0.92	1.17	2.15	1.15	0.50
noisy_watcher	1.32	1.59	1.05	2.27	1.62	0.60
SunameLLi	1.01	0.93	1.17	1.51	1.18	0.60
yharada	0.45	0.83	-	2.55	1.85	0.67

Round 1, Speak-Anytime Track, 5-player village

Team	Executed	Divined	Divination accuracy	Vote accuracy	Possessed avoidance
yharada	0.24	0.83	-	1.76	0.75
CanisLupus	2.40	-	-	2.00	1.00
Oxymoron	0.92	1.09	2.00	0.86	1.00
CamelliaDragons	0.51	1.00	1.71	0.67	1.00
wool_100%	1.37	1.82	1.20	1.00	1.00
noisy_watcher	0.78	1.12	1.71	1.80	-
SunameLLi	1.33	0.96	-	1.00	-

Round 2, 5-player village

Team	Executed	Divined	Divination accuracy	Vote accuracy	Possessed avoidance
yatolab	0.85	1.00	1.57	1.69	0.77
AGKAI	0.73	1.08	0.94	1.34	0.82
wool_100%	0.66	1.21	1.39	1.33	0.80
CanisLupus	1.34	0.98	1.40	1.23	0.89
yharada	0.55	0.70	1.22	0.97	0.59
NTT-HAI	0.81	0.76	0.56	1.14	0.64
ryanleeai	0.87	0.84	1.91	0.96	0.71
SunameLLi	0.89	1.19	0.78	1.87	0.58
CamelliaDragons	1.11	1.07	1.54	1.45	0.88
UEC-IL	0.87	0.69	0.78	1.01	0.95
Luna	0.83	1.00	0.82	0.98	0.72
carrot	0.93	0.58	1.15	1.06	0.47
noisy_watcher	1.46	0.84	0.40	1.28	0.38
Mackerel	1.21	0.77	0.70	1.20	0.80
yshimoda	1.26	1.16	0.98	0.77	0.74
Oxymoron	0.91	1.15	1.04	0.90	0.65
gotsumori-NLP	2.01	2.04	0.90	0.97	1.00
kataken	0.97	1.00	1.33	1.01	0.63

Round 2, 9-player village

Team	Executed	Divined	Guarded	Divination accuracy	Vote accuracy	Possessed avoidance
yharada	0.32	0.74	0.15	1.45	1.92	0.50
ryanleeai	0.62	0.85	1.77	2.60	1.67	0.50
SunameLLi	0.55	0.69	0.57	2.74	1.83	0.80
UEC-IL	0.70	0.72	0.71	1.09	2.31	0.83
noisy_watcher	0.94	0.96	1.91	1.05	1.34	0.75
wool_100%	0.76	1.03	1.47	1.10	1.46	1.00
Oxymoron	1.72	1.46	1.79	-	1.13	0.67
Mackerel	1.55	0.90	0.49	1.08	1.86	1.00
CanisLupus	1.29	0.45	-	-	1.44	-
yatolab	0.61	0.85	0.59	1.05	1.83	0.67
yshimoda	2.05	0.62	1.09	2.66	2.01	0.33
CamelliaDragons	2.38	2.12	0.61	-	1.76	0.60
carrot	1.30	1.34	0.71	-	1.15	0.50
kataken	0.71	1.89	1.75	1.87	1.62	0.67

Round 2, Speak-Anytime Track, 5-player village

Team	Executed	Divined	Divination accuracy	Vote accuracy	Possessed avoidance
yatolab	1.33	1.33	1.20	2.00	1.00
ryanleeai	1.87	1.29	-	2.00	1.00
wool_100%	1.20	0.75	2.00	2.50	0.33
SunameLLi	0.84	0.80	-	1.20	1.00
noisy_watcher	0.82	1.29	0.86	1.67	1.00
Oxymoron	0.86	1.12	4.00	2.67	0.50
yharada	0.31	0.92	2.40	0.86	0.50
kanolab	1.20	0.75	-	4.00	-
CanisLupus	1.20	1.45	2.00	0.67	1.00
UEC-IL	1.67	0.50	2.40	1.33	1.00
CamelliaDragons	0.69	0.92	1.20	0.80	-
kataken	0.28	0.97	-	0.35	1.00

Human Evaluation (Relative)

Human judges read selected game logs and evaluate the players of each game on each criterion. From 2024 winter onward the judges rank the players (average rank, lower is better); in the 2024 spring and 2024 international contests they gave 5-point scores (higher is better). In 13-player villages each entry (e.g. team-A, team-B) is evaluated separately.

Human evaluation was not conducted in this contest.

LLM-as-a-Judge (Relative Evaluation)

LLM judges rank the players of each game on each evaluation criterion; the ranks are averaged per team (lower is better). The judge models differ by contest and are listed under each track. The judge is published as aiwolf-nlp-llm-judge.

Round 1, 5-player village

Judge models: GPT-5.4・Gemini 2.5 Pro・Claude Sonnet 4.5 の 3 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Average
1	ryanleeai	1.18	1.45	2.04	2.20	1.47	1.67
2	Oxymoron	1.55	2.00	2.18	2.22	1.50	1.89
3	yharada	2.86	2.55	2.23	1.98	2.28	2.38
4	SunameLLi	2.66	2.87	2.57	2.72	2.89	2.74
5	noisy_watcher	2.91	2.93	2.72	2.63	2.94	2.83
6	kataken14f	2.97	3.05	2.63	2.52	3.11	2.86
7	wool_100%	3.11	3.36	2.75	2.99	3.18	3.08
8	CamelliaDragons	4.05	2.56	2.65	2.81	3.61	3.14
9	yshimoda	3.42	3.78	2.97	3.02	3.59	3.35
10	CanisLupus	3.98	4.32	3.60	3.51	3.72	3.83
11	gotsumori-NLP	3.81	3.90	4.24	3.44	4.20	3.92

Round 1, 9-player village

Judge models: GPT-5.4・Gemini 2.5 Pro・Claude Sonnet 4.5 の 3 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Team play	Average
1	ryanleeai	1.33	2.54	2.48	3.48	2.44	3.56	2.64
2	Oxymoron	2.61	3.70	3.30	4.30	2.22	4.61	3.46
3	yharada	5.30	4.28	2.85	2.63	4.46	3.98	3.92
4	CamelliaDragons	6.30	2.61	3.31	3.09	5.24	3.07	3.94
5	SunameLLi	4.52	4.39	3.98	4.37	4.52	4.83	4.43
6	noisy_watcher	4.41	6.06	6.04	5.39	5.72	5.43	5.51
7	yshimoda	5.46	6.41	5.06	5.61	6.06	5.32	5.65
8	wool_100%	6.93	6.89	6.26	5.07	7.15	5.50	6.30
9	CanisLupus	7.04	7.74	6.61	5.72	5.91	7.20	6.70

Round 1, Speak-Anytime Track, 5-player village

Judge models: GPT-5.4・Gemini 2.5 Pro・Claude Sonnet 4.5 の 3 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Average
1	Oxymoron	1.40	2.30	2.03	2.23	1.53	1.90
2	SunameLLi	2.10	2.27	2.13	2.27	2.83	2.32
3	yharada	2.97	3.07	2.43	1.87	3.10	2.69
4	noisy_watcher	2.67	2.53	3.50	3.43	2.67	2.96
5	wool_100%	3.30	3.40	3.00	3.40	3.13	3.25
6	CanisLupus	3.67	4.20	3.17	3.37	3.17	3.51
7	CamelliaDragons	4.73	3.20	3.87	3.07	4.53	3.88

Round 2, 5-player village

Judge models: GPT-5.6 Terra・Claude Sonnet 5・Gemini 3.1 Pro・gemma-4-31b・Qwen3.6-27b・Mistral-Small-3.2・EXAONE-4.5-33b・Seed-OSS-36b の 8 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Average
1	yharada	2.69	1.38	1.50	1.56	1.25	1.40
2	UEC-IL	1.50	1.75	2.69	4.19	3.50	2.20
3	ryanleeai	2.38	2.88	3.44	6.00	2.38	3.00
4	wool_100%	5.19	5.38	3.81	2.50	6.62	4.00
5	SunameLLi	8.12	6.00	6.38	6.19	6.69	5.90
6	AGKAI	9.12	8.19	10.00	6.75	7.75	8.10
7	Oxymoron	7.31	9.12	9.31	12.12	6.38	8.20
8	yatolab	13.75	8.19	8.00	5.44	12.94	9.10
9	yshimoda	4.62	9.25	10.06	15.62	7.25	9.70
10	NTT-HAI	12.12	11.25	8.50	6.19	12.56	10.10
11	kataken14f	13.12	8.88	10.06	9.25	11.50	10.60
12	CamelliaDragons	15.50	9.00	13.19	9.44	10.00	12.00
13	carrot	8.31	14.75	10.44	14.56	10.38	12.20
14	Luna	9.94	14.00	12.00	11.75	15.75	12.80
15	Mackerel	11.31	11.88	12.38	11.94	13.12	13.00
16	CanisLupus	13.12	15.12	14.56	13.88	7.94	13.70
17	gotsumori-NLP	16.62	16.38	17.50	16.38	17.25	17.40
18	noisy_watcher	16.25	17.62	17.19	17.25	17.75	17.60

Round 2, 9-player village

Judge models: GPT-5.6 Terra・Claude Sonnet 5・Gemini 3.1 Pro・gemma-4-31b・Qwen3.6-27b・Mistral-Small-3.2・EXAONE-4.5-33b・Seed-OSS-36b の 8 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Team play	Average
1	UEC-IL	2.00	1.50	2.25	3.38	5.12	2.25	1.75
2	yharada	3.62	2.38	2.25	2.50	1.62	2.94	2.08
3	ryanleeai	2.44	4.00	3.81	3.56	1.75	5.81	3.33
4	wool_100%	2.56	2.69	6.38	6.62	5.94	1.69	4.58
5	SunameLLi	8.25	6.38	5.44	6.56	5.75	5.19	5.50
6	kataken14f	9.25	5.38	5.25	5.62	8.19	7.12	6.67
7	noisy_watcher	6.12	6.19	6.38	7.12	8.06	5.50	6.75
8	yatolab	9.50	7.75	6.25	4.56	11.81	7.44	8.17
9	yshimoda	7.31	10.25	9.44	8.69	8.00	10.25	8.58
10	CanisLupus	10.50	11.75	10.56	10.25	5.88	12.00	10.33
11	Oxymoron	8.88	10.25	11.31	10.62	6.88	12.25	10.42
12	Mackerel	11.50	11.00	11.31	10.06	12.12	9.44	11.42
13	carrot	9.38	12.12	10.88	12.69	11.00	10.88	11.50
14	CamelliaDragons	13.69	13.38	13.50	12.75	12.88	12.25	13.92

Round 2, Speak-Anytime Track, 5-player village

Judge models: GPT-5.6 Terra・Claude Sonnet 5・Gemini 3.1 Pro・gemma-4-31b・Qwen3.6-27b・Mistral-Small-3.2・EXAONE-4.5-33b・Seed-OSS-36b の 8 モデル平均

#	Team	Natural expression	Contextual dialogue	Logical consistency	Action consistency	Character consistency	Average
1	yharada	1.25	1.56	1.19	2.50	1.00	1.00
2	UEC-IL	2.19	2.12	3.31	4.50	4.94	2.80
3	wool_100%	4.31	2.44	4.25	3.19	6.12	3.40
4	SunameLLi	5.00	5.00	5.81	4.56	3.69	4.40
5	ryanleeai	4.38	6.94	5.44	6.81	8.00	6.20
6	kataken14f	8.69	6.50	4.56	5.50	7.69	6.40
7	Oxymoron	7.00	7.06	7.94	8.06	5.31	7.00
8	yatolab	9.31	8.50	6.94	4.12	9.44	8.00
9	CanisLupus	8.75	10.62	11.50	11.00	4.44	9.60
10	noisy_watcher	7.75	9.25	8.31	8.62	11.56	9.60
11	kanolab	8.38	10.12	9.00	11.44	6.25	9.60
12	CamelliaDragons	11.00	7.88	9.75	7.69	9.56	10.00

Game Logs

Logs of the main competition. Only games that finished normally are listed.

Track	Games	Logs
Round 1, 5-player village	220	Log list
Round 1, 9-player village	18	Log list
Round 1, Speak-Anytime Track, 5-player village	14	Log list
Round 2, 5-player village	270	Log list
Round 2, 9-player village	28	Log list
Round 2, Speak-Anytime Track, 5-player village	24	Log list

How to view logs

Each “Log list” link opens a listing of the logs (.log files) of games that finished normally. A file name starts with the game start time, followed by the names of the participating teams.

View in the browser: press “▶ 開く” (open) in the “viewerで見る” (view in viewer) column of the row you want to read. aiwolf-nlp-viewer opens with that log loaded.
Save a file: press “⬇ 保存” (save) in the “ダウンロード” (download) column to download the log file. Clicking the file name shows the raw text of the log instead.
Save a whole folder: go one level up via “Parent directory/” and press “⬇ zip” in the row of the folder (e.g. success). All files in the folder are zipped in your browser and downloaded (a dialog confirms the number of files).

How to use the viewer is described in the “Log viewer” section of the Links page.