AI-ism character names

Test: Bad Writing Habits

Avg. Score

98.6%

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	Ministral 3B	100.0%	$0.0001	8.1s	100%
2	Stealth: Aurora Alpha	100.0%	$0.0000	9.8s	100%
3	Mistral Small Creative	100.0%	$0.0007	9.1s	100%
4	Ministral 3 3B	100.0%	$0.0005	11.1s	100%
5	Ministral 3 14B	100.0%	$0.0007	11.7s	100%
6	Gemini 3 Flash (Preview)	100.0%	$0.0078	19.6s	100%
7	DeepSeek V3 (2025-03-24)	100.0%	$0.0014	39.4s	100%
8	Ministral 8B	99.8%	$0.0004	10.4s	96%
9	Claude 3 Haiku	99.8%	$0.0025	14.9s	96%
10	Ministral 3 8B	99.8%	$0.0008	19.6s	96%
11	GPT-4o, May 13th (temp=1)	100.0%	$0.033	14.4s	100%
12	Arcee AI: Trinity Mini	99.6%	$0.0003	9.2s	94%
13	Z.AI GLM 4.7 Flash	100.0%	$0.0017	1.2m	100%
14	GPT-4o Mini (temp=1)	99.8%	$0.0012	34.8s	96%
15	Gemini 2.5 Flash	99.6%	$0.0052	10.6s	94%
16	Mistral Medium 3.1	99.8%	$0.0048	36.5s	96%
17	Gemini 2.5 Flash Lite	99.3%	$0.0009	9.5s	93%
18	GPT-4o, Aug. 6th (temp=1)	99.8%	$0.018	24.4s	96%
19	DeepSeek V3 (2024-12-26)	99.8%	$0.0021	54.6s	96%
20	Llama 3.1 Nemotron 70B	99.6%	$0.0038	31.7s	94%
21	GPT-4.1 Mini	99.3%	$0.0027	19.0s	93%
22	Llama 3.1 70B	99.3%	$0.0015	29.4s	93%
23	Hermes 3 70B	99.8%	$0.0010	1.2m	96%
24	Mistral Large 3	99.3%	$0.0033	30.3s	93%
25	Qwen 3.5 Plus (2026-02-15)	99.3%	$0.0060	31.5s	93%
26	GPT-4o, Aug. 6th (temp=0)	99.6%	$0.023	22.7s	94%
27	Z.AI GLM 4.6	99.6%	$0.0065	51.5s	94%
28	Claude 3.5 Haiku	98.9%	$0.0035	10.8s	91%
29	Cohere Command R+ (Aug. 2024)	99.8%	$0.020	52.5s	96%
30	Mistral Large	99.3%	$0.014	30.9s	93%
31	GPT-5 Nano	99.8%	$0.0042	1.4m	96%
32	Qwen 2.5 72B	99.1%	$0.0010	36.7s	92%
33	GPT-5 Mini	99.6%	$0.0100	57.4s	94%
34	DeepSeek-V2 Chat	99.3%	$0.0021	53.3s	93%
35	GPT-4.1 Nano	98.7%	$0.0007	13.3s	90%
36	Hermes 3 405B	99.3%	$0.0032	53.2s	93%
37	Mistral Large 2	99.1%	$0.013	29.4s	92%
38	Z.AI GLM 4.5	99.1%	$0.0051	42.1s	92%
39	o4 Mini	99.3%	$0.015	25.7s	91%
40	Writer: Palmyra X5	98.9%	$0.011	22.0s	91%
41	Rocinante 12B	98.9%	$0.0014	38.4s	91%
42	o4 Mini High	99.6%	$0.025	47.2s	94%
43	GPT-4o Mini (temp=0)	98.7%	$0.0012	34.8s	90%
44	Grok 4 Fast	98.4%	$0.0017	24.1s	89%
45	Z.AI GLM 4.7	99.6%	$0.010	1.4m	94%
46	GPT-4o, May 13th (temp=0)	99.1%	$0.035	14.1s	92%
47	Mistral NeMO	97.8%	$0.0005	10.1s	87%
48	Gemma 3 27B	98.4%	$0.0006	52.6s	89%
49	DeepSeek V3.1	99.3%	$0.0020	1.8m	93%
50	WizardLM 2 8x22b	99.1%	$0.0026	1.8m	92%
51	ByteDance Seed 1.6	99.8%	$0.013	2.5m	96%
52	GPT-4.1	98.2%	$0.018	44.7s	89%
53	Claude Sonnet 4.6	98.4%	$0.031	39.3s	89%
54	Grok 4.1 Fast	97.6%	$0.0018	37.8s	86%
55	Minimax M2.5	98.0%	$0.0034	1.3m	88%
56	Gemini 2.5 Pro	98.2%	$0.036	36.2s	89%
57	Grok 4	99.6%	$0.048	1.7m	94%
58	ByteDance Seed 1.6 Flash	96.9%	$0.0013	27.3s	84%
59	Gemini 3 Pro (Preview)	98.9%	$0.055	54.4s	91%
60	DeepSeek V3.2	98.7%	$0.0014	1.9m	88%
61	GPT-5.2	99.3%	$0.056	1.5m	93%
62	Gemma 3 12B	96.4%	$0.0004	41.3s	85%
63	Arcee AI: Trinity Large (Preview)	98.0%	$0.0000	43.6s	80%
64	Gemini 3.1 Pro (Preview)	100.0%	$0.107	1.8m	100%
65	Qwen 3.5 397B A17B	99.3%	$0.014	3.0m	93%
66	Gemma 3 4B	95.6%	$0.0002	20.0s	83%
67	Claude Haiku 4.5	96.0%	$0.011	21.6s	82%
68	Claude Opus 4.6	98.9%	$0.078	1.2m	91%
69	Claude 3.7 Sonnet	96.9%	$0.042	46.7s	84%
70	GPT-5.1	98.2%	$0.054	1.8m	89%
71	MoonshotAI: Kimi K2.5	98.7%	$0.019	3.2m	88%
72	Claude 3.5 Sonnet	96.2%	$0.048	35.5s	82%
73	Claude Sonnet 4.5	95.8%	$0.035	38.1s	81%
74	GPT-5	98.7%	$0.065	2.8m	90%
75	Mistral Small 3.2 24B	99.6%	$0.0069	5.7m	94%
76	Claude Sonnet 4	94.4%	$0.032	43.7s	78%
77	Z.AI GLM 5	94.4%	$0.0084	1.2m	75%
78	Claude Opus 4.5	94.7%	$0.070	53.4s	76%
79	Llama 3.1 8B	87.1%	$0.0003	1.3m	63%
80	Claude Opus 4	90.0%	$0.209	1.4m	64%
98.55%

Individual Scenarios

Detailed Writing Rules

▼

Fantasy: entering an ancient ruin

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	80	96.0%
DeepSeek V3.2	100	100	100	100	80	96.0%
Hermes 3 405B	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Hermes 3 70B	100	100	100	100	80	96.0%
Llama 3.1 8B	100	100	100	80	80	92.0%

▼

Horror: alone in an eerie place at night

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
Llama 3.1 8B	100	100	100	100	80	96.0%
Gemma 3 4B	100	100	100	100	80	96.0%
Claude Opus 4	100	100	100	80	80	92.0%

▼

Literary fiction: old friends reunite

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Llama 3.1 8B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	80	96.0%
Gemini 2.5 Pro	100	100	100	100	80	96.0%
Claude Sonnet 4	100	100	100	100	80	96.0%
Claude Sonnet 4.6	100	100	100	100	80	96.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	80	96.0%
Claude Haiku 4.5	100	100	100	100	80	96.0%
Claude 3.5 Haiku	100	100	100	100	80	96.0%
Writer: Palmyra X5	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
WizardLM 2 8x22b	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	80	96.0%
Z.AI GLM 5	100	100	100	80	80	92.0%
Claude 3.7 Sonnet	100	100	100	80	80	92.0%
Z.AI GLM 4.5	100	100	100	80	80	92.0%
ByteDance Seed 1.6 Flash	100	100	100	80	80	92.0%
Claude Opus 4.6	100	100	80	80	80	88.0%
Minimax M2.5	100	100	80	80	80	88.0%
Claude Sonnet 4.5	100	100	80	80	80	88.0%
Claude 3.5 Sonnet	100	100	80	80	60	84.0%
Claude Opus 4.5	80	80	80	80	80	80.0%
Claude Opus 4	100	80	80	60	60	76.0%

▼

Mystery: examining a crime scene

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	80	96.0%
Gemini 2.5 Pro	100	100	100	100	80	96.0%
GPT-5.2	100	100	100	100	80	96.0%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
Minimax M2.5	100	100	100	100	80	96.0%
Grok 4	100	100	100	100	80	96.0%
Claude Sonnet 4.6	100	100	100	100	80	96.0%
Claude Sonnet 4.5	100	100	100	100	80	96.0%
Grok 4.1 Fast	100	100	100	100	80	96.0%
GPT-4.1	100	100	100	100	80	96.0%
GPT-5 Nano	100	100	100	100	80	96.0%
Claude 3.5 Sonnet	100	100	100	100	80	96.0%
Z.AI GLM 4.5	100	100	100	100	80	96.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	80	96.0%
DeepSeek V3.1	100	100	100	100	80	96.0%
GPT-4o Mini (temp=0)	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	80	96.0%
Mistral NeMO	100	100	100	100	80	96.0%
GPT-5.1	100	100	100	80	80	92.0%
MoonshotAI: Kimi K2.5	100	100	100	100	60	92.0%
GPT-5	100	100	100	80	80	92.0%
Grok 4 Fast	100	100	100	80	80	92.0%
Claude Haiku 4.5	100	100	100	80	80	92.0%
DeepSeek V3.2	100	100	100	80	80	92.0%
ByteDance Seed 1.6 Flash	100	100	100	80	80	92.0%
Claude Opus 4.5	100	100	100	80	60	88.0%
Claude Opus 4	100	100	80	80	60	84.0%
Llama 3.1 8B	100	100	100	80	40	84.0%
Gemma 3 4B	100	80	80	80	80	84.0%
Z.AI GLM 5	100	100	100	60	40	80.0%
Arcee AI: Trinity Large (Preview)	100	100	100	80	20	80.0%

▼

Romance: separated couple reunites

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	80	96.0%
Gemini 2.5 Pro	100	100	100	100	80	96.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
Mistral Large 2	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Gemma 3 4B	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	80	96.0%
Claude Sonnet 4	100	100	100	80	80	92.0%
Claude 3.5 Sonnet	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	100	100	60	92.0%
Z.AI GLM 5	100	100	80	80	80	88.0%
Claude Opus 4	100	80	60	40	20	60.0%

▼

Thriller: chase through city streets

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	80	96.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	80	96.0%
Hermes 3 405B	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Grok 4.1 Fast	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	100	80	60	88.0%
Gemma 3 4B	100	100	80	80	80	88.0%

genre

▼

Fantasy: entering an ancient ruin

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	80	96.0%
Claude 3.7 Sonnet	100	100	100	100	80	96.0%
GPT-4.1	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	80	80	60	84.0%

▼

Horror: alone in an eerie place at night

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	80	96.0%
Llama 3.1 8B	100	80	60	60	40	68.0%

▼

Literary fiction: old friends reunite

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	80	96.0%
GPT-5	100	100	100	100	80	96.0%
Z.AI GLM 4.7	100	100	100	100	80	96.0%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
ByteDance Seed 1.6	100	100	100	100	80	96.0%
Z.AI GLM 4.6	100	100	100	100	80	96.0%
Grok 4 Fast	100	100	100	100	80	96.0%
Claude 3.5 Haiku	100	100	100	100	80	96.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	80	96.0%
Mistral NeMO	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	80	96.0%
Claude Sonnet 4.5	100	100	100	80	80	92.0%
Claude 3.5 Sonnet	100	100	100	80	80	92.0%
Gemini 2.5 Flash Lite	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	100	80	80	92.0%
Claude Haiku 4.5	100	100	80	80	80	88.0%
Claude 3.7 Sonnet	100	100	80	80	60	84.0%
Claude Opus 4.5	100	100	100	60	40	80.0%
Gemma 3 12B	80	80	80	80	80	80.0%
Claude Sonnet 4	100	80	80	60	60	76.0%
Claude Opus 4	100	80	60	60	40	68.0%

▼

Mystery: examining a crime scene

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	80	96.0%
GPT-5.1	100	100	100	100	80	96.0%
Claude Opus 4.5	100	100	100	100	80	96.0%
GPT-5.2	100	100	100	100	80	96.0%
Claude Sonnet 4.6	100	100	100	100	80	96.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	80	96.0%
Grok 4 Fast	100	100	100	100	80	96.0%
Mistral Large 3	100	100	100	100	80	96.0%
DeepSeek-V2 Chat	100	100	100	100	80	96.0%
Z.AI GLM 4.5	100	100	100	100	80	96.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	80	96.0%
Mistral Medium 3.1	100	100	100	100	80	96.0%
Gemini 2.5 Flash	100	100	100	100	80	96.0%
Hermes 3 405B	100	100	100	100	80	96.0%
GPT-4o Mini (temp=1)	100	100	100	100	80	96.0%
GPT-4o Mini (temp=0)	100	100	100	100	80	96.0%
Llama 3.1 Nemotron 70B	100	100	100	100	80	96.0%
WizardLM 2 8x22b	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	80	96.0%
Qwen 3.5 397B A17B	100	100	100	80	80	92.0%
Claude Sonnet 4	100	100	100	100	60	92.0%
GPT-4.1	100	100	100	80	80	92.0%
GPT-4o, May 13th (temp=0)	100	100	100	80	80	92.0%
Claude 3.7 Sonnet	100	100	100	80	80	92.0%
GPT-4.1 Mini	100	100	100	80	80	92.0%
Llama 3.1 70B	100	100	100	80	80	92.0%
Mistral Large	100	100	100	80	80	92.0%
Qwen 2.5 72B	100	100	100	80	80	92.0%
Mistral Small 3.2 24B	100	100	100	80	80	92.0%
GPT-4.1 Nano	100	100	100	80	80	92.0%
Z.AI GLM 5	100	100	100	80	60	88.0%
Claude 3.5 Sonnet	100	100	80	80	80	88.0%
Mistral Large 2	100	100	80	80	80	88.0%
Arcee AI: Trinity Large (Preview)	100	100	100	80	60	88.0%
Llama 3.1 8B	100	100	100	80	60	88.0%
Claude Opus 4	100	100	100	60	60	84.0%
Claude Sonnet 4.5	100	80	80	80	80	84.0%
Grok 4.1 Fast	100	100	80	80	60	84.0%
Claude Haiku 4.5	100	100	80	80	60	84.0%
ByteDance Seed 1.6 Flash	100	100	80	80	60	84.0%
Gemma 3 4B	100	80	80	80	80	84.0%
Mistral NeMO	80	80	80	80	80	80.0%

▼

Romance: separated couple reunites

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	80	96.0%
Gemini 2.5 Pro	100	100	100	100	80	96.0%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
Claude Sonnet 4.5	100	100	100	100	80	96.0%
GPT-4.1	100	100	100	100	80	96.0%
Claude 3.5 Sonnet	100	100	100	100	80	96.0%
Mistral Large 3	100	100	100	100	80	96.0%
DeepSeek-V2 Chat	100	100	100	100	80	96.0%
Claude 3.7 Sonnet	100	100	100	100	80	96.0%
Claude Haiku 4.5	100	100	100	100	80	96.0%
DeepSeek V3.1	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Gemma 3 4B	100	100	100	100	80	96.0%
Claude Sonnet 4	100	100	100	80	80	92.0%
Llama 3.1 8B	100	80	60	40	40	64.0%

▼

Thriller: chase through city streets

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	80	96.0%
Claude Haiku 4.5	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Gemma 3 4B	100	100	100	100	80	96.0%
Claude Opus 4	100	100	100	100	60	92.0%
Llama 3.1 8B	100	100	80	60	40	76.0%

Novelcrafter Default Prompt

▼

Fantasy: entering an ancient ruin

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	80	96.0%
Minimax M2.5	100	100	100	100	80	96.0%
Writer: Palmyra X5	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Claude 3 Haiku	100	100	100	100	80	96.0%
Gemma 3 4B	100	100	100	100	80	96.0%
Grok 4.1 Fast	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	80	80	80	88.0%

▼

Horror: alone in an eerie place at night

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Llama 3.1 8B	100	100	80	60	40	76.0%

▼

Literary fiction: old friends reunite

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	80	96.0%
Claude Opus 4.5	100	100	100	100	80	96.0%
Z.AI GLM 4.7	100	100	100	100	80	96.0%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
Minimax M2.5	100	100	100	100	80	96.0%
Grok 4	100	100	100	100	80	96.0%
GPT-4.1	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
Gemini 2.5 Flash Lite	100	100	100	100	80	96.0%
Llama 3.1 Nemotron 70B	100	100	100	100	80	96.0%
Qwen 2.5 72B	100	100	100	100	80	96.0%
Ministral 3 8B	100	100	100	100	80	96.0%
Llama 3.1 8B	100	100	100	100	80	96.0%
WizardLM 2 8x22b	100	100	100	100	80	96.0%
MoonshotAI: Kimi K2.5	100	100	100	80	80	92.0%
Claude 3.7 Sonnet	100	100	100	80	80	92.0%
Gemma 3 12B	100	100	100	80	80	92.0%
Claude Sonnet 4	100	100	80	80	80	88.0%
Claude 3.5 Sonnet	100	100	100	80	60	88.0%
Claude Haiku 4.5	100	100	100	80	60	88.0%
Z.AI GLM 5	100	100	60	60	60	76.0%

▼

Mystery: examining a crime scene

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	80	96.0%
Claude Opus 4.6	100	100	100	100	80	96.0%
GPT-5.2	100	100	100	100	80	96.0%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
GPT-4.1	100	100	100	100	80	96.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	80	96.0%
Claude 3.5 Sonnet	100	100	100	100	80	96.0%
Mistral Large 3	100	100	100	100	80	96.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	80	96.0%
DeepSeek-V2 Chat	100	100	100	100	80	96.0%
DeepSeek V3.2	100	100	100	100	80	96.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	80	96.0%
GPT-4.1 Mini	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
DeepSeek V3.1	100	100	100	100	80	96.0%
Writer: Palmyra X5	100	100	100	100	80	96.0%
Gemini 2.5 Flash	100	100	100	100	80	96.0%
Llama 3.1 70B	100	100	100	100	80	96.0%
Mistral Large	100	100	100	100	80	96.0%
Gemma 3 27B	100	100	100	100	80	96.0%
Qwen 2.5 72B	100	100	100	100	80	96.0%
Llama 3.1 8B	100	100	100	100	80	96.0%
Ministral 8B	100	100	100	100	80	96.0%
WizardLM 2 8x22b	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	80	96.0%
o4 Mini High	100	100	100	80	80	92.0%
MoonshotAI: Kimi K2.5	100	100	100	80	80	92.0%
GPT-5	100	100	100	80	80	92.0%
o4 Mini	100	100	100	100	60	92.0%
Minimax M2.5	100	100	100	80	80	92.0%
Grok 4.1 Fast	100	100	100	80	80	92.0%
Arcee AI: Trinity Mini	100	100	100	80	80	92.0%
Gemma 3 4B	100	100	100	80	80	92.0%
Gemini 2.5 Pro	100	100	80	80	80	88.0%
Claude Sonnet 4.6	100	100	80	80	80	88.0%
Claude 3.5 Haiku	100	100	80	80	80	88.0%
Mistral NeMO	100	100	80	80	80	88.0%
GPT-5.1	100	100	80	80	80	88.0%
Grok 4 Fast	100	100	80	80	80	88.0%
Claude Haiku 4.5	100	100	80	80	80	88.0%
GPT-4o Mini (temp=0)	100	80	80	80	80	84.0%
GPT-4.1 Nano	100	80	80	80	80	84.0%
Z.AI GLM 5	100	80	80	80	60	80.0%
Claude Sonnet 4	100	100	80	60	60	80.0%
Claude Sonnet 4.5	100	80	80	80	40	76.0%
Claude Opus 4.5	100	80	60	60	60	72.0%
Claude Opus 4	100	80	60	60	40	68.0%

▼

Romance: separated couple reunites

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	80	96.0%
Llama 3.1 8B	100	100	100	100	80	96.0%
Claude Opus 4.5	100	100	100	80	80	92.0%
Claude 3.7 Sonnet	100	100	100	80	80	92.0%
DeepSeek V3.2	100	100	100	100	60	92.0%
Writer: Palmyra X5	100	100	100	80	80	92.0%
Claude Sonnet 4	100	100	80	80	80	88.0%

▼

Thriller: chase through city streets

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100.0%
Claude 3.5 Haiku	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	80	96.0%
ByteDance Seed 1.6 Flash	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	80	80	92.0%
Llama 3.1 8B	100	100	100	100	60	92.0%
Gemma 3 4B	100	100	100	80	80	92.0%

AI-ism character names

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

Detailed Writing Rules

Fantasy: entering an ancient ruin

Horror: alone in an eerie place at night

Literary fiction: old friends reunite

Mystery: examining a crime scene

Romance: separated couple reunites

Thriller: chase through city streets

genre

Fantasy: entering an ancient ruin

Horror: alone in an eerie place at night

Literary fiction: old friends reunite

Mystery: examining a crime scene

Romance: separated couple reunites

Thriller: chase through city streets

Novelcrafter Default Prompt

Fantasy: entering an ancient ruin

Horror: alone in an eerie place at night

Literary fiction: old friends reunite

Mystery: examining a crime scene

Romance: separated couple reunites

Thriller: chase through city streets