Count dialogue tags

Test: Dialogue tags

Avg. Score

85.7%

Scenarios

Overall Performance

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

Rank ▲	Model	Score	Avg. Cost	Avg. Time	Stability
1	Mistral Small 4	100.0%	$0.0002	2.9s	100%
2	Gemini 3.1 Flash Lite (Preview)	100.0%	$0.0004	2.0s	100%
3	GPT-4o Mini (temp=0)	100.0%	$0.0002	3.4s	100%
4	Gemini 3.1 Flash Lite	100.0%	$0.0004	2.0s	100%
5	Mistral Small 3.2 24B	100.0%	$0.0001	4.1s	100%
6	Claude 3 Haiku	100.0%	$0.0004	3.4s	100%
7	Grok 4 Fast	100.0%	$0.0003	4.2s	100%
8	Gemini 3.1 Flash Lite (Reasoning)	100.0%	$0.0004	3.6s	100%
9	DeepSeek V4 Flash (Reasoning)	100.0%	$0.0001	6.3s	100%
10	DeepSeek V4 Flash	100.0%	$0.0001	6.8s	100%
11	Gemma 3 12B	100.0%	$0.0000	7.4s	100%
12	Gemini 3 Flash (Preview)	100.0%	$0.0009	3.2s	100%
13	Ministral 3 14B	100.0%	$0.0001	8.2s	100%
14	Grok 4.20	100.0%	$0.0007	4.9s	100%
15	Qwen3 235B A22B Instruct 2507	100.0%	$0.0001	8.3s	100%
16	Mistral Medium 3.1	100.0%	$0.0006	6.1s	100%
17	Mistral Large 3	100.0%	$0.0005	7.2s	100%
18	Llama 3.1 Nemotron 70B	100.0%	$0.0001	9.6s	100%
19	DeepSeek V3 (2024-12-26)	100.0%	$0.0004	10.1s	100%
20	Grok 4.1 Fast	100.0%	$0.0003	10.2s	100%
21	Gemma 3 27B	100.0%	$0.0001	12.5s	100%
22	DeepSeek V3 (2025-03-24)	100.0%	$0.0003	14.6s	100%
23	Mistral Small 4 (Reasoning)	100.0%	$0.0010	11.0s	100%
24	GPT-4o Mini (temp=1)	100.0%	$0.0002	15.5s	100%
25	Gemini 3.5 Flash (Reasoning, Minimal)	100.0%	$0.0025	2.6s	100%
26	DeepSeek V3.1	100.0%	$0.0002	15.4s	100%
27	Gemma 4 31B	100.0%	$0.0001	15.9s	100%
28	DeepSeek-V2 Chat	100.0%	$0.0001	16.1s	100%
29	Stealth: Hunter Alpha	100.0%	$0.0000	16.9s	100%
30	GPT-4.1	100.0%	$0.0023	4.7s	100%
31	Hermes 3 405B	100.0%	$0.0000	17.7s	100%
32	Gemma 4 26B	100.0%	$0.0001	17.2s	100%
33	Mistral Large 2	100.0%	$0.0019	8.1s	100%
34	GPT-4o, Aug. 6th (temp=0)	100.0%	$0.0030	3.8s	100%
35	GPT-4o, Aug. 6th (temp=1)	100.0%	$0.0030	3.7s	100%
36	Writer: Palmyra X5	100.0%	$0.0021	8.8s	100%
37	Aion 2.0	100.0%	$0.0011	16.7s	100%
38	Z.AI GLM 4.7 Flash	100.0%	$0.0006	24.6s	100%
39	Z.AI GLM 5 Turbo	100.0%	$0.0033	9.9s	100%
40	DeepSeek V4 Pro	100.0%	$0.0009	25.1s	100%
41	Claude Sonnet 4	100.0%	$0.0044	7.2s	100%
42	GPT-4o, May 13th (temp=0)	100.0%	$0.0048	5.2s	100%
43	Claude Sonnet 4.5	100.0%	$0.0045	7.3s	100%
44	GPT-4o, May 13th (temp=1)	100.0%	$0.0049	5.5s	100%
45	Claude 3.5 Sonnet	100.0%	$0.0049	6.2s	100%
46	Claude 3.7 Sonnet	100.0%	$0.0050	7.1s	100%
47	GPT-5.4	100.0%	$0.0048	9.6s	100%
48	Gemini 3 Flash (Preview, Reasoning)	100.0%	$0.0048	10.1s	100%
49	GPT-5.1	100.0%	$0.0049	12.4s	100%
50	GPT-5.4 (Reasoning, Low)	100.0%	$0.0060	10.3s	100%
51	Qwen 3.6 35B	100.0%	$0.0044	24.7s	100%
52	Claude Opus 4.5	100.0%	$0.0077	8.7s	100%
53	Gemini 2.5 Flash Lite	96.1%	$0.0001	1.4s	76%
54	Claude Opus 4.6	100.0%	$0.0079	9.5s	100%
55	GPT-5.4 (Reasoning)	100.0%	$0.0073	15.2s	100%
56	Llama 3.1 70B	96.1%	$0.0003	3.2s	76%
57	Mistral Large	100.0%	$0.0091	8.4s	100%
58	GPT-5.5	100.0%	$0.0091	9.1s	100%
59	Z.AI GLM 4.5	96.1%	$0.0005	5.8s	76%
60	Claude Opus 4.6 (Reasoning)	100.0%	$0.0091	10.3s	100%
61	Grok 4.20 (Beta)	96.1%	$0.0016	1.9s	76%
62	Grok 4	100.0%	$0.0080	18.1s	100%
63	Z.AI GLM 5.1	100.0%	$0.0060	30.6s	100%
64	Z.AI GLM 4.7	100.0%	$0.0027	51.3s	100%
65	Claude Opus 4.7 (Reasoning)	100.0%	$0.011	6.8s	100%
66	Gemma 4 31B (Reasoning)	100.0%	$0.0004	1.1m	100%
67	Xiaomi MIMO v2.5 Pro	96.1%	$0.0014	10.3s	76%
68	Claude Opus 4.7	100.0%	$0.011	7.2s	100%
69	Z.AI GLM 4.6	100.0%	$0.0033	51.6s	100%
70	MoonshotAI: Kimi K2.5	100.0%	$0.0053	40.7s	100%
71	GPT-5.5 (Reasoning, Low)	100.0%	$0.011	11.1s	100%
72	Gemma 4 26B (Reasoning)	100.0%	$0.0011	1.2m	100%
73	Z.AI GLM 5	100.0%	$0.0049	50.1s	100%
74	GPT-5.5 (Reasoning)	100.0%	$0.012	11.2s	100%
75	Gemini 3.5 Flash (Reasoning)	100.0%	$0.013	7.5s	100%
76	Xiaomi MIMO v2.5	92.1%	$0.0009	6.1s	69%
77	Claude Haiku 4.5	92.1%	$0.0016	4.0s	69%
78	Claude Sonnet 4.6 (Reasoning)	96.1%	$0.0054	8.4s	76%
79	Mistral Small Creative	88.2%	$0.0001	2.2s	64%
80	Gemini 2.5 Flash Lite (Reasoning)	92.1%	$0.0006	20.1s	69%
81	Gemini 3 Pro (Preview)	100.0%	$0.017	13.7s	100%
82	Claude Sonnet 4.6	92.1%	$0.0046	7.7s	69%
83	Qwen 3.5 Plus (2026-04-20)	100.0%	$0.0086	59.6s	100%
84	GPT-5.2	92.1%	$0.0046	9.8s	69%
85	GPT-5 Nano	96.1%	$0.0023	58.8s	76%
86	GPT-4.1 Mini	87.4%	$0.0004	3.3s	45%
87	DeepSeek V4 Pro (Reasoning)	100.0%	$0.0085	1.6m	100%
88	DeepSeek V3.2	90.0%	$0.0002	13.7s	40%
89	Claude Opus 4	100.0%	$0.023	15.8s	100%
90	Cohere Command R+ (Aug. 2024)	87.4%	$0.0030	7.0s	45%
91	Inception Mercury 2	79.5%	$0.0009	1.9s	44%
92	Gemini 2.5 Pro	96.1%	$0.015	14.6s	76%
93	Gemini 2.5 Flash (Reasoning)	87.4%	$0.0035	7.1s	45%
94	Z.AI GLM 4.5 Air	83.5%	$0.0005	15.4s	44%
95	GPT-5 Mini	90.0%	$0.0022	14.1s	40%
96	Gemini 3.1 Pro (Preview)	100.0%	$0.024	23.5s	100%
97	Qwen 3.6 27B	96.1%	$0.010	54.4s	76%
98	Qwen 3.5 27B	100.0%	$0.016	1.3m	100%
99	o4 Mini High	96.1%	$0.014	34.7s	76%
100	ByteDance Seed 1.6	90.0%	$0.0023	27.7s	40%
101	GPT-5.4 Mini (Reasoning)	78.2%	$0.0020	3.7s	37%
102	Qwen 3.5 122B	100.0%	$0.022	56.5s	100%
103	Grok 4.3 (Reasoning)	100.0%	$0.018	1.4m	100%
104	Stealth: Healer Alpha	74.8%	$0.0000	6.3s	32%
105	MoonshotAI: Kimi K2.6	100.0%	$0.015	1.6m	100%
106	Gemini 2.5 Flash	74.4%	$0.0009	2.5s	31%
107	Qwen 3.6 Flash	90.0%	$0.0063	22.6s	40%
108	Qwen 3.5 Plus (2026-02-15)	81.5%	$0.0008	13.3s	26%
109	GPT-5	100.0%	$0.027	51.7s	100%
110	GPT-4.1 Nano	69.7%	$0.0001	2.9s	23%
111	Grok 4.20 (Reasoning)	90.0%	$0.0067	36.2s	40%
112	Grok 4.3	68.9%	$0.0006	4.0s	19%
113	GPT-5.4 Mini	67.0%	$0.0014	2.2s	22%
114	Qwen 3 32B	67.0%	$0.0004	23.9s	22%
115	Hermes 3 70B	64.9%	$0.0001	12.7s	17%
116	MiniMax M2.5	86.2%	$0.0044	1.2m	39%
117	GPT-OSS 120B	68.8%	$0.0002	29.8s	18%
118	Mistral NeMO	47.9%	$0.0000	4.0s	24%
119	Arcee AI: Trinity Mini	51.9%	$0.0001	3.9s	19%
120	Grok 4.20 (Beta, Reasoning)	90.0%	$0.019	14.1s	40%
121	Qwen 2.5 72B	57.5%	$0.0001	7.5s	14%
122	o4 Mini	72.1%	$0.0063	15.9s	22%
123	Qwen3.6 Max Preview	100.0%	$0.027	1.7m	100%
124	ByteDance Seed 1.6 Flash	52.3%	$0.0003	6.9s	15%
125	Qwen3.7 Max	100.0%	$0.034	1.2m	100%
126	LFM2 24B	48.9%	$0.0000	7.1s	9%
127	Ministral 3 8B	37.0%	$0.0001	2.0s	12%
128	Arcee AI: Trinity Large (Preview)	47.6%	$0.0000	6.8s	3%
129	Nemotron 3 Nano	66.1%	$0.0009	50.4s	10%
130	Rocinante 12B	48.9%	$0.0002	14.5s	4%
131	Inception Mercury	42.5%	$0.0002	2.2s	4%
132	Qwen 3.5 Flash	70.0%	$0.0030	51.7s	8%
133	Ministral 3B	40.2%	$0.0000	1.8s	2%
134	Gemma 3 4B	33.8%	$0.0000	3.4s	5%
135	Ministral 3 3B	29.8%	$0.0000	1.5s	7%
136	Llama 3.1 8B	33.8%	$0.0001	1.3s	1%
137	GPT-5.4 Mini (Reasoning, Low)	31.1%	$0.0016	3.2s	7%
138	MiniMax M2.7	86.1%	$0.0081	2.1m	38%
139	Nemotron 3 Super	56.1%	$0.0000	56.2s	5%
140	ByteDance Seed 2.0 Mini	60.0%	$0.0011	1.0m	2%
141	Qwen 3.5 9B	71.4%	$0.0012	1.8m	12%
142	WizardLM 2 8x22b	25.6%	$0.0005	12.6s	6%
143	Qwen 3.5 397B A17B	100.0%	$0.026	3.1m	100%
144	Ministral 8B	19.9%	$0.0000	2.1s	1%
145	Stealth: Aurora Alpha	49.7%	—	3.3s	11%
146	GPT-5.4 Nano	12.9%	$0.0004	2.1s	0%
147	GPT-5.4 Nano (Reasoning, Low)	9.1%	$0.0004	2.0s	1%
148	GPT-5.4 Nano (Reasoning)	8.9%	$0.0004	2.3s	0%
149	Qwen 3.5 35B	70.0%	$0.016	53.3s	8%
150	ByteDance Seed 2.0 Lite	0.0%	$0.0028	33.4s	0%
85.71%

Individual Scenarios

▼

Write unattributed dialogue

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Avg ▼
Qwen3.7 Max	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen3.6 Max Preview	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5.1	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5 Turbo	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.5 Flash (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4.3 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4.7 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.5 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.5 (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.6	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 4 31B (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 122B	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-04-20)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 4 26B (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 27B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V4 Pro (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4.7	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100	100	100	100	100	100.0%
Aion 2.0	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.6 35B	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V4 Flash (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100	100	100	100	100	100.0%
Stealth: Hunter Alpha	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 4 31B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.5 Flash (Reasoning, Minimal)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 4 26B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4	100	100	100	100	100	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V4 Pro	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Small 4 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V4 Flash	100	100	100	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4.20	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen3 235B A22B Instruct 2507	100	100	100	100	100	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100	100	100	100	100	100.0%
Mistral Small 4	100	100	100	100	100	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	61	96.1%
o4 Mini High	100	100	100	100	100	100	100	100	100	61	96.1%
Qwen 3.6 27B	100	100	100	100	100	100	100	100	100	61	96.1%
Gemini 2.5 Pro	100	100	100	100	100	100	100	100	100	61	96.1%
Xiaomi MIMO v2.5 Pro	100	100	100	100	100	100	100	100	100	61	96.1%
Z.AI GLM 4.5	100	100	100	100	100	100	100	100	100	61	96.1%
Grok 4.20 (Beta)	100	100	100	100	100	100	100	100	100	61	96.1%
GPT-5 Nano	100	100	100	100	100	100	100	100	100	61	96.1%
Gemini 2.5 Flash Lite	100	100	100	100	100	100	100	100	100	61	96.1%
Llama 3.1 70B	100	100	100	100	100	100	100	100	100	61	96.1%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100	61	61	92.1%
GPT-5.2	100	100	100	100	100	100	100	100	61	61	92.1%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100	61	61	92.1%
Claude Haiku 4.5	100	100	100	100	100	100	100	100	61	61	92.1%
Xiaomi MIMO v2.5	100	100	100	100	100	100	100	100	61	61	92.1%
GPT-5 Mini	100	100	100	100	100	100	100	100	100	0	90.0%
Grok 4.20 (Beta, Reasoning)	100	100	100	100	100	100	100	100	100	0	90.0%
Grok 4.20 (Reasoning)	100	100	100	100	100	100	100	100	100	0	90.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100	100	0	90.0%
Qwen 3.6 Flash	100	100	100	100	100	100	100	100	100	0	90.0%
DeepSeek V3.2	100	100	100	100	100	100	100	100	100	0	90.0%
Mistral Small Creative	100	100	100	100	100	100	100	61	61	61	88.2%
Gemini 2.5 Flash (Reasoning)	100	100	100	100	100	100	100	100	61	14	87.4%
GPT-4.1 Mini	100	100	100	100	100	100	100	100	61	14	87.4%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100	100	100	61	14	87.4%
MiniMax M2.5	100	100	100	100	100	100	100	100	61	1	86.2%
MiniMax M2.7	100	100	100	100	100	100	100	100	61	0	86.1%
Z.AI GLM 4.5 Air	100	100	100	100	100	100	100	61	61	14	83.5%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100	100	100	14	1	81.5%
Inception Mercury 2	100	100	100	100	100	100	61	61	61	14	79.5%
GPT-5.4 Mini (Reasoning)	100	100	100	100	100	100	61	61	61	0	78.2%
Stealth: Healer Alpha	100	100	100	100	100	100	61	61	14	14	74.8%
Gemini 2.5 Flash	100	100	100	100	100	61	61	61	61	1	74.4%
o4 Mini	100	100	100	100	100	100	61	61	0	0	72.1%
Qwen 3.5 9B	100	100	100	100	100	100	100	14	0	0	71.4%
Qwen 3.5 35B	100	100	100	100	100	100	100	0	0	0	70.0%
Qwen 3.5 Flash	100	100	100	100	100	100	100	0	0	0	70.0%
GPT-4.1 Nano	100	100	100	100	100	61	61	61	14	1	69.7%
Grok 4.3	100	100	100	100	100	100	61	14	14	1	68.9%
GPT-OSS 120B	100	100	100	100	100	100	61	14	14	0	68.8%
GPT-5.4 Mini	100	100	100	100	61	61	61	61	14	14	67.0%
Qwen 3 32B	100	100	100	100	61	61	61	61	14	14	67.0%
Nemotron 3 Nano	100	100	100	100	100	100	61	0	0	0	66.1%
Hermes 3 70B	100	100	100	100	100	61	61	14	14	1	64.9%
ByteDance Seed 2.0 Mini	100	100	100	100	100	100	0	0	0	0	60.0%
Qwen 2.5 72B	100	100	100	100	61	61	14	14	14	14	57.5%
Nemotron 3 Super	100	100	100	100	100	61	0	0	0	0	56.1%
ByteDance Seed 1.6 Flash	100	100	100	61	61	61	14	14	14	0	52.3%
Arcee AI: Trinity Mini	100	100	61	61	61	61	61	14	1	1	51.9%
Stealth: Aurora Alpha	100	100	100	61	61	61	14	1	0	0	49.7%
LFM2 24B	100	100	100	61	61	14	14	14	14	14	48.9%
Rocinante 12B	100	100	100	100	61	14	14	1	0	0	48.9%
Mistral NeMO	100	61	61	61	61	61	61	14	1	0	47.9%
Arcee AI: Trinity Large (Preview)	100	100	100	100	61	14	1	1	0	0	47.6%
Inception Mercury	100	100	100	61	61	1	1	1	0	0	42.5%
Ministral 3B	100	100	100	61	14	14	14	1	0	0	40.2%
Ministral 3 8B	100	61	61	61	61	14	14	0	0	0	37.0%
Gemma 3 4B	100	61	61	61	14	14	14	14	1	1	33.8%
Llama 3.1 8B	100	100	61	61	14	1	1	1	0	0	33.8%
GPT-5.4 Mini (Reasoning, Low)	61	61	61	61	14	14	14	14	14	1	31.1%
Ministral 3 3B	61	61	61	61	14	14	14	14	1	0	29.8%
WizardLM 2 8x22b	100	61	14	14	14	14	14	14	14	1	25.6%
Ministral 8B	61	61	61	14	1	1	1	0	0	0	19.9%
GPT-5.4 Nano	100	14	14	1	1	0	0	0	0	0	12.9%
GPT-5.4 Nano (Reasoning, Low)	61	14	14	1	1	1	0	0	0	0	9.1%
GPT-5.4 Nano (Reasoning)	61	14	14	1	0	0	0	0	0	0	8.9%
ByteDance Seed 2.0 Lite	0	0	0	0	0	0	0	0	0	0	0.0%

Count dialogue tags

Overall Performance

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)

Individual Scenarios

Write unattributed dialogue