Past progressive (was/were + -ing) overuse

Test: Bad Writing Habits

Avg. Score

90.2%

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	GPT-4.1 Mini	100.0%	$0.0027	19.0s	100%
2	Grok 4 Fast	100.0%	$0.0017	24.1s	100%
3	Grok 4.1 Fast	100.0%	$0.0018	37.8s	100%
4	GPT-4o, Aug. 6th (temp=1)	100.0%	$0.018	24.4s	100%
5	o4 Mini	99.8%	$0.015	25.7s	97%
6	Stealth: Aurora Alpha	98.7%	$0.0000	9.8s	86%
7	GPT-4o Mini (temp=1)	99.5%	$0.0012	34.8s	90%
8	o4 Mini High	100.0%	$0.025	47.2s	100%
9	GPT-4.1	99.8%	$0.018	44.7s	96%
10	GPT-5 Mini	99.7%	$0.0100	57.4s	96%
11	GPT-5 Nano	99.9%	$0.0042	1.4m	98%
12	GPT-4o Mini (temp=0)	98.5%	$0.0012	34.8s	83%
13	Claude 3 Haiku	96.6%	$0.0025	14.9s	78%
14	GPT-4o, Aug. 6th (temp=0)	98.7%	$0.023	22.7s	82%
15	GPT-4o, May 13th (temp=1)	98.1%	$0.033	14.4s	77%
16	Grok 4	100.0%	$0.048	1.7m	100%
17	GPT-5.2	100.0%	$0.056	1.5m	100%
18	DeepSeek-V2 Chat	96.7%	$0.0021	53.3s	74%
19	ByteDance Seed 1.6 Flash	95.9%	$0.0013	27.3s	68%
20	GPT-5.1	100.0%	$0.054	1.8m	100%
21	Llama 3.1 Nemotron 70B	96.1%	$0.0038	31.7s	68%
22	Writer: Palmyra X5	95.8%	$0.011	22.0s	67%
23	DeepSeek V3 (2025-03-24)	96.1%	$0.0014	39.4s	66%
24	Qwen 3.5 Plus (2026-02-15)	94.9%	$0.0060	31.5s	64%
25	GPT-4o, May 13th (temp=0)	95.8%	$0.035	14.1s	69%
26	Arcee AI: Trinity Mini	93.1%	$0.0003	9.2s	59%
27	Gemini 2.5 Flash	94.0%	$0.0052	10.6s	59%
28	Hermes 3 405B	95.3%	$0.0032	53.2s	66%
29	Hermes 3 70B	95.9%	$0.0010	1.2m	68%
30	Cohere Command R+ (Aug. 2024)	96.4%	$0.020	52.5s	68%
31	Qwen 2.5 72B	92.6%	$0.0010	36.7s	64%
32	Gemini 2.5 Flash Lite	93.0%	$0.0009	9.5s	56%
33	Claude 3.7 Sonnet	96.8%	$0.042	46.7s	71%
34	Z.AI GLM 4.5	93.4%	$0.0051	42.1s	59%
35	Mistral Medium 3.1	92.2%	$0.0048	36.5s	59%
36	DeepSeek V3 (2024-12-26)	93.3%	$0.0021	54.6s	59%
37	GPT-5	100.0%	$0.065	2.8m	100%
38	Claude Sonnet 4.5	93.7%	$0.035	38.1s	62%
39	Claude 3.5 Sonnet	94.3%	$0.048	35.5s	64%
40	Gemma 3 12B	90.9%	$0.0004	41.3s	52%
41	GPT-4.1 Nano	88.9%	$0.0007	13.3s	49%
42	Arcee AI: Trinity Large (Preview)	90.8%	$0.0000	43.6s	51%
43	Mistral NeMO	88.0%	$0.0005	10.1s	48%
44	Gemma 3 4B	88.5%	$0.0002	20.0s	50%
45	MoonshotAI: Kimi K2.5	97.8%	$0.019	3.2m	80%
46	Claude Sonnet 4	92.3%	$0.032	43.7s	58%
47	Llama 3.1 8B	92.5%	$0.0003	1.3m	51%
48	Mistral Large	88.9%	$0.014	30.9s	50%
49	Mistral Large 2	89.0%	$0.013	29.4s	49%
50	Mistral Large 3	87.9%	$0.0033	30.3s	46%
51	WizardLM 2 8x22b	91.8%	$0.0026	1.8m	57%
52	ByteDance Seed 1.6	95.0%	$0.013	2.5m	64%
53	Rocinante 12B	87.6%	$0.0014	38.4s	44%
54	Llama 3.1 70B	85.6%	$0.0015	29.4s	40%
55	Mistral Small Creative	83.8%	$0.0007	9.1s	37%
56	Qwen 3.5 397B A17B	92.8%	$0.014	3.0m	61%
57	Gemini 3.1 Pro (Preview)	96.2%	$0.107	1.8m	72%
58	DeepSeek V3.2	86.9%	$0.0014	1.9m	49%
59	Ministral 3 3B	82.2%	$0.0005	11.1s	31%
60	Z.AI GLM 5	85.8%	$0.0084	1.2m	41%
61	Ministral 8B	79.0%	$0.0004	10.4s	35%
62	Claude Opus 4.5	87.8%	$0.070	53.4s	50%
63	Claude Haiku 4.5	79.4%	$0.011	21.6s	34%
64	Gemma 3 27B	80.7%	$0.0006	52.6s	32%
65	Claude Opus 4.6	88.3%	$0.078	1.2m	50%
66	Ministral 3 14B	76.4%	$0.0007	11.7s	28%
67	Ministral 3 8B	76.7%	$0.0008	19.6s	29%
68	Minimax M2.5	80.5%	$0.0034	1.3m	34%
69	Gemini 2.5 Pro	80.0%	$0.036	36.2s	38%
70	Claude 3.5 Haiku	76.3%	$0.0035	10.8s	22%
71	Gemini 3 Flash (Preview)	72.1%	$0.0078	19.6s	25%
72	Ministral 3B	70.1%	$0.0001	8.1s	19%
73	DeepSeek V3.1	76.3%	$0.0020	1.8m	32%
74	Gemini 3 Pro (Preview)	76.5%	$0.055	54.4s	30%
75	Claude Opus 4	94.0%	$0.209	1.4m	62%
76	Z.AI GLM 4.6	69.7%	$0.0065	51.5s	22%
77	Claude Sonnet 4.6	71.3%	$0.031	39.3s	22%
78	Z.AI GLM 4.7	66.7%	$0.010	1.4m	17%
79	Z.AI GLM 4.7 Flash	60.8%	$0.0017	1.2m	14%
80	Mistral Small 3.2 24B	82.8%	$0.0069	5.7m	33%
90.16%

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%
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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
GPT-4.1	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%
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-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	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%
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%
Hermes 3 70B	100	100	100	100	100	100.0%
Claude 3 Haiku	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%
Rocinante 12B	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	97	99.4%
Mistral Medium 3.1	100	100	100	100	94	98.8%
Claude Sonnet 4.5	100	100	100	100	82	96.4%
Mistral Large 3	100	100	100	100	78	95.6%
Mistral Small Creative	100	100	100	100	75	95.0%
Claude Sonnet 4	100	100	100	100	73	94.5%
Claude Sonnet 4.6	100	100	100	100	71	94.2%
Mistral Large 2	100	100	100	100	70	94.0%
Mistral Large	100	100	100	97	68	92.9%
Gemma 3 27B	100	100	100	86	77	92.7%
DeepSeek V3.2	100	100	100	100	50	90.0%
Z.AI GLM 4.6	100	100	100	100	48	89.7%
Qwen 2.5 72B	100	100	100	74	73	89.4%
Arcee AI: Trinity Mini	100	100	100	100	47	89.3%
WizardLM 2 8x22b	100	100	100	100	44	88.7%
Z.AI GLM 4.7	100	100	100	87	44	86.2%
Arcee AI: Trinity Large (Preview)	100	100	100	100	21	84.2%
Mistral Small 3.2 24B	100	100	89	86	42	83.4%
Gemini 3 Pro (Preview)	100	100	100	100	0	80.0%
Claude 3.5 Haiku	100	100	100	100	0	80.0%
Llama 3.1 8B	100	100	100	100	0	80.0%
Z.AI GLM 4.7 Flash	100	100	86	83	0	73.8%
Ministral 3B	100	100	100	50	0	70.0%
Ministral 3 8B	100	100	100	28	8	67.1%
Ministral 3 14B	100	100	100	10	2	62.3%
Gemini 3 Flash (Preview)	93	84	51	50	0	55.5%
Ministral 8B	91	81	54	50	0	55.2%
Ministral 3 3B	100	89	64	0	0	50.6%

▼

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%
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%
GPT-5.2	100	100	100	100	100	100.0%
Claude Opus 4	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%
GPT-4.1	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	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-V2 Chat	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%
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%
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%
Gemma 3 12B	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	98	99.6%
DeepSeek V3 (2024-12-26)	100	100	100	100	93	98.6%
Cohere Command R+ (Aug. 2024)	100	100	100	100	88	97.6%
GPT-5 Nano	100	100	99	96	93	97.5%
Llama 3.1 Nemotron 70B	100	100	100	100	85	97.0%
Claude Opus 4.6	100	100	100	100	85	96.9%
ByteDance Seed 1.6	100	100	100	100	82	96.5%
Mistral Large 3	100	100	100	93	89	96.4%
Claude Opus 4.5	100	100	100	95	83	95.7%
Claude 3 Haiku	100	100	100	100	78	95.6%
DeepSeek V3 (2025-03-24)	100	100	100	100	69	93.9%
Mistral Small Creative	100	100	100	100	65	93.0%
Minimax M2.5	100	100	99	98	67	93.0%
Ministral 3 3B	100	100	100	94	67	92.2%
Mistral Small 3.2 24B	100	100	100	100	59	91.8%
Z.AI GLM 4.5	100	100	100	80	69	89.9%
GPT-4o, May 13th (temp=0)	100	100	100	100	46	89.3%
Arcee AI: Trinity Mini	100	100	100	100	41	88.3%
Ministral 3B	100	100	100	89	48	87.5%
Arcee AI: Trinity Large (Preview)	100	100	100	87	43	85.9%
Claude Sonnet 4.6	100	100	100	100	25	84.9%
Stealth: Aurora Alpha	100	100	100	72	46	83.5%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	17	83.5%
Gemma 3 4B	100	100	100	58	56	82.8%
Claude 3.7 Sonnet	100	100	100	95	13	81.7%
Mistral Large 2	100	100	100	88	19	81.4%
Gemini 2.5 Pro	100	100	92	59	49	80.0%
Claude Sonnet 4.5	100	100	100	100	0	80.0%
Mistral Large	100	100	100	100	0	80.0%
Ministral 3 14B	100	100	100	100	0	80.0%
GPT-4.1 Nano	100	100	100	64	34	79.6%
Gemini 3 Pro (Preview)	100	100	100	90	1	78.3%
WizardLM 2 8x22b	100	100	100	48	43	78.2%
Llama 3.1 70B	100	100	86	54	48	77.7%
DeepSeek V3.2	100	100	97	48	18	72.6%
Writer: Palmyra X5	100	100	81	80	0	72.2%
Claude 3.5 Haiku	100	100	100	61	0	72.2%
Qwen 2.5 72B	100	100	69	66	25	72.2%
Hermes 3 405B	100	100	100	37	0	67.5%
Rocinante 12B	100	100	100	28	6	66.9%
Gemma 3 27B	100	100	69	60	4	66.7%
Claude Sonnet 4	100	100	72	46	0	63.6%
Gemini 3 Flash (Preview)	100	100	69	33	0	60.4%
Z.AI GLM 4.7	100	100	100	0	0	60.0%
Llama 3.1 8B	100	100	100	0	0	60.0%
Gemini 2.5 Flash Lite	100	100	80	0	0	56.0%
Ministral 8B	100	80	71	26	0	55.4%
Mistral NeMO	100	66	64	26	21	55.3%
Z.AI GLM 4.6	100	74	66	30	0	54.1%
Claude Haiku 4.5	100	88	29	10	0	45.2%
DeepSeek V3.1	100	68	33	5	0	41.2%
Ministral 3 8B	100	40	28	4	0	34.4%
Z.AI GLM 4.7 Flash	100	37	29	0	0	33.3%

▼

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%
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%
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%
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%
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%
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%
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%
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 3B	100	100	100	100	100	100.0%
Llama 3.1 8B	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%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	98	99.6%
Z.AI GLM 4.5	100	100	100	97	96	98.5%
Hermes 3 405B	100	100	100	100	92	98.5%
DeepSeek V3.2	100	100	100	100	92	98.4%
Claude 3.7 Sonnet	100	100	100	95	95	98.0%
Ministral 3B	100	100	100	100	84	96.8%
Ministral 3 14B	100	100	100	100	67	93.5%
Gemma 3 12B	100	100	100	97	65	92.3%
Gemma 3 27B	100	100	100	84	73	91.3%
Z.AI GLM 5	100	100	100	100	53	90.7%
Mistral Small Creative	100	100	100	100	36	87.2%
Arcee AI: Trinity Large (Preview)	100	100	100	85	46	86.2%
Claude Sonnet 4.5	100	100	100	77	45	84.5%
DeepSeek V3.1	100	100	100	65	52	83.3%
Claude Haiku 4.5	100	100	100	53	49	80.4%
Gemini 3 Flash (Preview)	100	100	100	100	0	80.0%
Llama 3.1 70B	100	100	100	100	0	80.0%
Arcee AI: Trinity Mini	100	100	100	100	0	80.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	0	80.0%
Gemini 3 Pro (Preview)	100	100	92	84	0	75.4%
Ministral 3 8B	100	100	72	50	28	70.2%
Ministral 8B	100	100	91	32	0	64.7%
Rocinante 12B	100	100	57	50	0	61.4%
Z.AI GLM 4.7 Flash	100	71	48	38	0	51.4%
Z.AI GLM 4.7	95	82	47	20	0	48.7%

▼

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%
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%
GPT-5.2	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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
GPT-4.1	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-V2 Chat	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%
Mistral Medium 3.1	100	100	100	100	100	100.0%
Writer: Palmyra X5	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%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100.0%
Hermes 3 70B	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%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	94	98.8%
Llama 3.1 70B	100	100	100	100	92	98.5%
Qwen 2.5 72B	100	100	100	100	92	98.3%
Mistral Large 2	100	100	100	98	91	97.7%
Mistral NeMO	100	100	100	100	86	97.2%
Gemini 2.5 Flash	100	100	100	100	82	96.4%
Z.AI GLM 4.6	100	100	100	100	82	96.3%
Claude 3.7 Sonnet	100	100	100	100	80	96.0%
Mistral Large 3	100	100	100	100	80	95.9%
Gemma 3 4B	100	100	100	100	76	95.2%
ByteDance Seed 1.6	100	100	100	100	68	93.7%
DeepSeek V3.2	100	100	100	100	64	92.8%
Gemini 2.5 Flash Lite	100	100	100	100	64	92.8%
Ministral 3 8B	100	100	100	100	62	92.4%
GPT-4o Mini (temp=0)	100	100	100	94	53	89.4%
ByteDance Seed 1.6 Flash	100	100	100	100	44	88.8%
GPT-4o, May 13th (temp=0)	100	100	100	99	41	88.1%
Claude Sonnet 4.5	100	100	100	100	31	86.1%
Claude Haiku 4.5	100	100	100	67	53	84.0%
DeepSeek V3.1	100	100	100	100	20	84.0%
Claude Sonnet 4.6	100	100	100	94	11	81.1%
Ministral 3B	100	100	100	100	4	80.8%
Mistral Small Creative	100	100	100	100	0	80.0%
Ministral 3 3B	100	100	100	100	0	80.0%
Arcee AI: Trinity Mini	100	100	100	92	0	78.5%
DeepSeek V3 (2024-12-26)	100	100	100	91	0	78.1%
Arcee AI: Trinity Large (Preview)	100	100	100	36	28	72.7%
GPT-4.1 Nano	100	100	100	54	0	70.8%
Mistral Small 3.2 24B	100	100	100	53	0	70.6%
Minimax M2.5	100	100	100	40	0	68.1%
Claude Opus 4.5	100	100	86	48	5	68.0%
Z.AI GLM 5	100	100	100	36	0	67.3%
Ministral 8B	100	100	83	50	0	66.6%
Claude 3.5 Haiku	100	100	100	15	0	63.0%
Gemma 3 27B	100	100	100	12	0	62.4%
Ministral 3 14B	100	88	64	58	0	62.0%
Gemini 3 Pro (Preview)	100	100	56	24	0	55.9%
Gemini 2.5 Pro	100	100	26	11	1	47.6%
Gemini 3 Flash (Preview)	100	68	46	19	0	46.6%
Z.AI GLM 4.7	100	78	0	0	0	35.5%
Z.AI GLM 4.7 Flash	90	21	0	0	0	22.2%

▼

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%
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%
Claude Sonnet 4	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%
GPT-4.1	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%
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, 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%
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 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%
Qwen 2.5 72B	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 3B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	93	98.7%
Z.AI GLM 4.5	100	100	100	100	87	97.4%
Claude Haiku 4.5	100	100	100	100	84	96.9%
Gemma 3 27B	100	100	100	100	84	96.9%
DeepSeek V3.2	100	100	100	100	84	96.7%
ByteDance Seed 1.6 Flash	100	100	100	93	86	95.7%
Ministral 3 14B	100	100	100	100	77	95.3%
Claude Opus 4.5	100	100	100	96	80	95.2%
Gemini 2.5 Flash Lite	100	100	100	100	76	95.2%
Gemini 3 Flash (Preview)	100	100	100	100	72	94.4%
Arcee AI: Trinity Mini	100	100	100	100	71	94.1%
Gemini 3 Pro (Preview)	100	100	100	100	58	91.5%
Gemma 3 12B	100	100	100	100	53	90.6%
Arcee AI: Trinity Large (Preview)	100	100	100	100	50	90.0%
Ministral 8B	100	100	100	91	53	88.9%
Gemini 2.5 Pro	100	100	100	100	40	88.0%
Mistral Large 3	100	100	100	100	38	87.7%
Ministral 3 8B	100	100	88	84	62	86.8%
GPT-4.1 Nano	100	100	100	100	30	86.0%
Mistral Medium 3.1	100	100	100	98	31	85.8%
Minimax M2.5	100	100	100	99	26	84.9%
Mistral NeMO	100	100	100	93	15	81.6%
Claude Sonnet 4.6	100	100	100	100	0	80.0%
Llama 3.1 8B	100	100	100	100	0	80.0%
Z.AI GLM 4.7 Flash	100	100	100	87	11	79.4%
Ministral 3B	100	100	85	79	17	76.3%
Mistral Small 3.2 24B	100	100	100	45	0	69.0%
Rocinante 12B	100	100	100	43	0	68.6%
Z.AI GLM 4.6	100	100	100	25	0	64.9%
Llama 3.1 70B	100	100	100	0	0	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%
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%
GPT-5.2	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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
GPT-4.1	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%
Grok 4 Fast	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=1)	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%
Writer: Palmyra X5	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%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Claude 3 Haiku	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%
Arcee AI: Trinity Large (Preview)	100	100	100	100	97	99.5%
Claude Sonnet 4.6	100	100	100	100	87	97.4%
Rocinante 12B	100	100	100	100	87	97.4%
Ministral 8B	100	100	100	100	84	96.8%
Mistral Medium 3.1	100	100	100	100	80	95.9%
Claude Opus 4.6	100	100	100	100	77	95.3%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	77	95.3%
Mistral Large 3	100	100	100	100	71	94.1%
Mistral Small Creative	100	100	100	100	70	94.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	68	93.6%
WizardLM 2 8x22b	100	100	100	100	65	93.1%
Arcee AI: Trinity Mini	100	100	100	100	53	90.7%
Z.AI GLM 4.7 Flash	100	100	100	100	49	89.9%
Llama 3.1 Nemotron 70B	100	100	100	100	45	89.0%
Claude 3.5 Sonnet	100	100	100	100	43	88.6%
DeepSeek V3.2	100	100	100	84	55	87.9%
DeepSeek V3 (2025-03-24)	100	100	100	100	37	87.5%
Claude Opus 4.5	100	100	100	95	40	87.1%
Z.AI GLM 5	100	100	100	64	60	84.7%
Claude Sonnet 4.5	100	100	100	100	22	84.3%
Claude Haiku 4.5	100	100	100	67	52	83.7%
Mistral Large 2	100	100	98	93	19	82.0%
Qwen 2.5 72B	100	100	100	57	53	81.8%
Gemini 3 Flash (Preview)	100	100	100	99	8	81.3%
Mistral NeMO	100	100	92	67	41	80.1%
DeepSeek-V2 Chat	100	100	100	100	0	80.0%
Gemini 2.5 Flash	100	100	100	100	0	80.0%
Claude Sonnet 4	100	100	100	95	0	78.9%
Hermes 3 70B	100	100	100	68	25	78.5%
GPT-4.1 Nano	100	100	95	93	0	77.7%
Ministral 3 8B	100	100	100	40	37	75.4%
Mistral Large	100	100	69	59	41	73.9%
DeepSeek V3.1	100	100	80	58	21	72.0%
Gemini 3 Pro (Preview)	100	100	74	59	26	71.8%
Ministral 3 14B	100	100	97	47	0	68.8%
Gemma 3 4B	100	100	100	35	0	67.1%
Llama 3.1 70B	100	100	100	35	0	66.9%
Gemini 2.5 Pro	100	71	68	53	32	64.8%
Claude 3.5 Haiku	100	87	74	61	0	64.5%
Ministral 3B	100	100	100	0	0	60.0%
Gemma 3 12B	100	100	48	8	0	51.2%
Z.AI GLM 4.6	100	84	60	0	0	48.8%
Ministral 3 3B	100	100	15	0	0	43.0%
Mistral Small 3.2 24B	100	100	0	0	0	40.0%
Gemma 3 27B	100	57	25	11	0	38.7%
Z.AI GLM 4.7	100	15	10	8	5	27.7%

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%
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%
Z.AI GLM 5	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%
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%
GPT-4.1	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-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%
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-4.1 Mini	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%
GPT-4o Mini (temp=0)	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%
Qwen 2.5 72B	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%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	95	98.9%
DeepSeek V3.2	100	100	100	100	93	98.6%
Claude Opus 4.6	100	100	100	100	90	98.0%
Hermes 3 70B	100	100	100	100	84	96.7%
Llama 3.1 8B	100	100	100	100	79	95.8%
GPT-4o, May 13th (temp=1)	100	100	100	100	78	95.6%
ByteDance Seed 1.6 Flash	100	100	100	100	77	95.4%
MoonshotAI: Kimi K2.5	100	100	100	100	74	94.8%
Claude Sonnet 4	100	100	100	100	72	94.4%
DeepSeek V3.1	100	100	100	100	70	94.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	67	93.3%
Gemma 3 27B	100	100	100	100	55	91.0%
Gemma 3 4B	100	100	100	100	54	90.8%
DeepSeek V3 (2024-12-26)	100	100	100	100	53	90.6%
Gemini 3 Flash (Preview)	100	100	100	100	53	90.5%
Z.AI GLM 4.6	100	100	100	94	54	89.7%
Gemini 2.5 Flash	100	100	100	96	48	88.8%
Gemma 3 12B	100	100	100	100	41	88.3%
Writer: Palmyra X5	100	100	100	100	35	87.1%
Z.AI GLM 4.5	100	100	100	100	33	86.7%
Claude 3 Haiku	100	100	100	100	26	85.1%
Ministral 8B	100	100	100	85	33	83.8%
Gemini 3 Pro (Preview)	100	100	100	96	21	83.5%
Arcee AI: Trinity Large (Preview)	100	100	100	100	10	81.9%
Mistral Medium 3.1	100	100	100	98	10	81.8%
GPT-4o, May 13th (temp=0)	100	100	100	79	28	81.3%
Claude Opus 4.5	100	100	100	100	0	80.0%
Mistral Large 3	100	100	100	100	0	80.0%
Mistral Large	100	100	100	100	0	80.0%
Mistral Small 3.2 24B	100	100	100	100	0	80.0%
Rocinante 12B	100	100	100	100	0	80.0%
Claude 3.5 Sonnet	100	100	100	44	18	72.4%
Minimax M2.5	100	100	100	48	13	72.2%
Claude 3.5 Haiku	100	100	100	48	0	69.7%
Z.AI GLM 4.7 Flash	100	95	62	53	30	67.8%
Ministral 3 14B	100	100	100	27	0	65.4%
Claude Sonnet 4.6	100	100	100	0	0	60.0%
Ministral 3B	100	100	100	0	0	60.0%
Llama 3.1 70B	100	100	77	20	0	59.3%
Z.AI GLM 4.7	100	56	55	44	0	51.1%
Mistral Small Creative	100	76	54	2	0	46.4%

▼

Horror: alone in an eerie place at night

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
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%
GPT-5.2	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%
GPT-5 Nano	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	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%
GPT-4.1 Mini	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	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%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	99	99.8%
DeepSeek V3 (2024-12-26)	100	100	100	100	99	99.8%
Mistral Large	100	100	100	100	97	99.3%
Claude 3.7 Sonnet	100	100	100	100	93	98.7%
DeepSeek V3 (2025-03-24)	100	100	100	100	92	98.5%
Gemma 3 12B	100	100	100	100	88	97.5%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	86	97.1%
GPT-4.1	100	100	100	100	83	96.6%
Hermes 3 70B	100	100	100	100	81	96.2%
GPT-5 Mini	100	100	100	100	80	96.1%
Claude Opus 4	100	100	100	100	79	95.9%
Claude Opus 4.5	100	100	100	100	68	93.6%
Qwen 2.5 72B	100	100	100	84	81	92.9%
Claude Sonnet 4.5	100	100	98	97	67	92.3%
Z.AI GLM 4.6	100	100	87	86	79	90.4%
GPT-4o Mini (temp=1)	100	100	100	100	51	90.1%
DeepSeek-V2 Chat	100	100	100	77	71	89.5%
Gemini 2.5 Flash	100	100	97	84	58	87.8%
MoonshotAI: Kimi K2.5	100	100	100	100	21	84.2%
Mistral Medium 3.1	100	100	100	100	16	83.1%
Mistral Large 3	100	100	100	86	29	83.1%
Llama 3.1 8B	100	100	100	100	5	81.1%
Llama 3.1 70B	100	100	100	100	0	80.0%
Mistral Small 3.2 24B	100	100	100	100	0	80.0%
Arcee AI: Trinity Mini	100	100	100	100	0	80.0%
DeepSeek V3.2	100	100	80	70	50	80.0%
Minimax M2.5	100	100	88	59	51	79.6%
Ministral 3 8B	100	100	100	74	13	77.4%
Claude Sonnet 4	100	97	92	83	14	77.2%
Claude 3.5 Sonnet	100	100	100	56	27	76.6%
Z.AI GLM 4.5	100	100	94	79	9	76.2%
Qwen 3.5 397B A17B	100	93	72	53	53	74.3%
Writer: Palmyra X5	100	100	100	55	17	74.3%
Gemma 3 4B	100	100	100	68	0	73.5%
ByteDance Seed 1.6 Flash	100	100	80	62	7	69.9%
Mistral Small Creative	100	100	100	33	0	66.7%
Qwen 3.5 Plus (2026-02-15)	100	88	79	46	1	62.9%
Claude Sonnet 4.6	100	100	65	46	3	62.8%
Rocinante 12B	100	100	100	14	0	62.8%
Gemini 2.5 Pro	100	81	75	48	7	62.2%
Gemini 2.5 Flash Lite	100	100	100	0	0	60.0%
Claude Haiku 4.5	100	100	99	0	0	59.9%
ByteDance Seed 1.6	100	90	79	21	0	57.8%
Mistral Large 2	100	100	53	30	2	57.1%
GPT-4.1 Nano	100	100	82	0	0	56.6%
Ministral 3 3B	100	100	74	5	0	55.8%
DeepSeek V3.1	100	100	39	37	0	55.1%
Gemini 3.1 Pro (Preview)	69	59	45	25	21	43.7%
Ministral 3 14B	100	55	31	27	0	42.7%
Ministral 8B	100	100	13	0	0	42.5%
Z.AI GLM 5	100	100	4	0	0	40.8%
Claude Opus 4.6	89	62	51	0	0	40.2%
Gemini 3 Flash (Preview)	100	72	26	0	0	39.6%
Z.AI GLM 4.7	100	57	29	0	0	37.1%
Gemma 3 27B	88	85	3	0	0	35.1%
Z.AI GLM 4.7 Flash	100	48	19	0	0	33.3%
Gemini 3 Pro (Preview)	100	36	29	0	0	32.8%
Claude 3.5 Haiku	41	41	15	0	0	19.5%
Ministral 3B	61	27	0	0	0	17.6%

▼

Literary fiction: old friends reunite

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%
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%
GPT-5.2	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%
GPT-4.1	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%
GPT-4o, May 13th (temp=0)	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%
Writer: Palmyra X5	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 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%
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%
Arcee AI: Trinity Mini	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%
GPT-4.1 Nano	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	96	99.2%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	92	98.5%
Gemma 3 27B	100	100	100	100	90	97.9%
Claude Haiku 4.5	100	100	100	100	84	96.9%
Mistral NeMO	100	100	100	100	84	96.7%
DeepSeek V3.2	100	100	100	100	82	96.4%
Gemini 3 Pro (Preview)	100	100	100	91	88	95.8%
Gemini 2.5 Pro	100	100	100	93	86	95.7%
Claude 3.7 Sonnet	100	100	100	100	75	95.0%
DeepSeek-V2 Chat	100	100	100	100	74	94.8%
Qwen 3.5 397B A17B	100	100	100	100	70	94.0%
Gemini 2.5 Flash Lite	100	100	100	100	67	93.3%
Claude Opus 4.5	100	100	100	100	58	91.5%
Claude Opus 4.6	100	100	100	100	54	90.8%
Arcee AI: Trinity Large (Preview)	100	100	100	100	53	90.7%
Ministral 8B	100	100	100	100	48	89.7%
Claude Opus 4	100	100	100	82	67	89.7%
MoonshotAI: Kimi K2.5	100	100	100	76	69	88.9%
Claude 3.5 Haiku	100	100	100	100	43	88.6%
Gemini 2.5 Flash	100	100	100	100	43	88.6%
Mistral Medium 3.1	100	100	100	94	44	87.7%
Mistral Large 3	100	100	100	100	29	85.8%
Gemini 3 Flash (Preview)	100	99	98	92	33	84.4%
Claude 3.5 Sonnet	100	100	100	100	8	81.5%
DeepSeek V3 (2024-12-26)	100	100	100	89	16	81.0%
Mistral Large	100	100	100	64	37	80.1%
Ministral 3 3B	100	100	100	65	35	80.0%
Z.AI GLM 4.7	100	100	100	99	0	79.9%
Z.AI GLM 4.7 Flash	100	100	100	88	0	77.7%
Z.AI GLM 5	100	100	90	82	3	74.9%
Ministral 3B	100	99	79	62	29	73.7%
DeepSeek V3.1	100	100	56	49	44	69.8%
Mistral Large 2	100	100	89	33	17	67.7%
Minimax M2.5	100	96	63	55	9	64.7%
Ministral 3 8B	100	100	61	8	0	53.6%
Z.AI GLM 4.6	94	54	38	3	0	37.9%
Claude Sonnet 4.6	85	46	28	0	0	31.6%

▼

Mystery: examining a crime scene

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
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%
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%
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%
GPT-4.1	100	100	100	100	100	100.0%
GPT-5 Nano	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-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, 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%
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%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Llama 3.1 8B	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	97	99.5%
ByteDance Seed 1.6	100	100	100	97	96	98.7%
Gemini 3.1 Pro (Preview)	100	100	96	94	92	96.5%
Llama 3.1 70B	100	100	100	100	80	96.0%
Claude 3.5 Sonnet	100	100	100	100	79	95.8%
Cohere Command R+ (Aug. 2024)	100	100	100	100	74	94.8%
Claude 3 Haiku	100	100	100	93	79	94.4%
Qwen 2.5 72B	100	100	100	100	69	93.9%
Mistral NeMO	100	100	100	88	80	93.6%
Stealth: Aurora Alpha	100	100	100	82	80	92.4%
Claude Opus 4.5	100	100	100	94	68	92.4%
GPT-4.1 Nano	100	100	100	77	77	90.8%
Ministral 8B	100	100	100	86	62	89.6%
Mistral Medium 3.1	100	100	100	78	62	88.0%
Mistral Large 3	100	100	100	93	36	85.9%
GPT-4o Mini (temp=0)	100	100	100	92	37	85.8%
Z.AI GLM 4.5	100	100	100	99	19	83.5%
Mistral Small Creative	100	100	100	100	14	82.8%
DeepSeek V3 (2025-03-24)	100	100	100	100	0	80.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	0	80.0%
Hermes 3 70B	100	100	100	100	0	80.0%
Gemma 3 12B	100	100	100	52	46	79.6%
Claude Opus 4.6	100	100	88	63	43	78.7%
DeepSeek V3.2	100	100	100	91	0	78.1%
Qwen 3.5 Plus (2026-02-15)	100	100	99	77	13	77.7%
ByteDance Seed 1.6 Flash	100	100	100	85	0	77.0%
Mistral Small 3.2 24B	100	100	89	64	31	76.7%
Ministral 3 3B	100	100	100	56	21	75.4%
Z.AI GLM 5	100	100	90	84	0	74.9%
Claude Opus 4	100	100	100	45	8	70.7%
Claude Sonnet 4	100	94	80	68	10	70.3%
Mistral Large	100	100	100	47	0	69.3%
Ministral 3 14B	100	100	100	46	0	69.2%
WizardLM 2 8x22b	100	100	73	64	0	67.5%
Z.AI GLM 4.7	100	100	97	37	0	66.9%
Mistral Large 2	100	82	81	52	0	63.0%
Gemini 3 Pro (Preview)	100	100	65	45	0	61.9%
Claude Haiku 4.5	100	100	38	26	0	52.8%
Z.AI GLM 4.7 Flash	100	95	65	0	0	52.0%
Ministral 3 8B	100	100	29	29	0	51.6%
Claude Sonnet 4.6	100	74	49	28	0	50.2%
Minimax M2.5	100	100	50	0	0	50.0%
DeepSeek V3.1	100	100	27	13	0	47.9%
Ministral 3B	100	79	29	0	0	41.6%
Qwen 3.5 397B A17B	77	75	14	14	8	37.5%
Gemini 2.5 Pro	96	44	27	19	0	37.2%
Z.AI GLM 4.6	58	34	0	0	0	18.5%
Gemini 3 Flash (Preview)	67	0	0	0	0	13.5%

▼

Romance: separated couple reunites

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
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%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100.0%
GPT-5.2	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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
GPT-4.1	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%
Grok 4 Fast	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	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%
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%
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%
Mistral Large	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	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%
Llama 3.1 8B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	98	99.6%
Z.AI GLM 4.5	100	100	100	100	97	99.5%
Mistral Large 2	100	100	100	100	96	99.2%
Arcee AI: Trinity Large (Preview)	100	100	100	100	90	98.1%
o4 Mini	100	100	100	100	86	97.3%
Hermes 3 70B	100	100	100	100	85	97.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	74	94.8%
Gemma 3 27B	100	100	100	100	70	94.0%
GPT-4.1 Nano	100	100	100	100	67	93.3%
Ministral 3 14B	100	100	98	90	77	93.2%
Gemini 2.5 Pro	100	100	100	97	65	92.3%
Z.AI GLM 5	100	100	100	95	63	91.7%
Claude 3.5 Sonnet	100	100	100	87	65	90.5%
Qwen 2.5 72B	100	100	100	100	52	90.4%
Qwen 3.5 397B A17B	100	100	100	100	49	89.8%
Claude Sonnet 4.5	100	100	100	100	47	89.3%
Gemini 3 Flash (Preview)	100	100	100	100	46	89.3%
DeepSeek-V2 Chat	100	100	100	88	55	88.7%
Mistral Medium 3.1	100	100	100	87	50	87.3%
Claude Opus 4	100	100	100	100	34	86.8%
Claude Opus 4.6	100	100	100	99	28	85.5%
Rocinante 12B	100	100	100	100	25	84.9%
Ministral 8B	100	100	100	71	52	84.6%
DeepSeek V3.1	100	100	100	100	21	84.2%
Claude Opus 4.5	100	100	92	63	60	83.1%
Z.AI GLM 4.7 Flash	100	100	100	63	52	83.1%
Llama 3.1 Nemotron 70B	100	100	100	100	15	83.0%
Z.AI GLM 4.7	100	100	100	100	10	81.9%
DeepSeek V3 (2025-03-24)	100	100	100	100	0	80.0%
Mistral Small Creative	100	100	100	100	0	80.0%
Ministral 3 8B	100	100	100	100	0	80.0%
Mistral NeMO	100	100	100	100	0	80.0%
DeepSeek V3 (2024-12-26)	100	83	78	71	68	79.9%
Mistral Large 3	100	100	100	84	13	79.2%
DeepSeek V3.2	100	100	100	91	0	78.3%
Z.AI GLM 4.6	100	100	100	55	25	76.1%
Claude Haiku 4.5	100	100	100	46	9	70.9%
Gemma 3 4B	100	100	73	25	10	61.4%
Gemini 3 Pro (Preview)	100	95	66	24	2	57.4%
Minimax M2.5	88	84	84	0	0	51.2%
Claude Sonnet 4.6	87	80	31	3	0	40.3%
Ministral 3B	100	85	10	0	0	38.9%

▼

Thriller: chase through city streets

Model	# 1	# 2	# 3	# 4	# 5	Avg ▼
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%
GPT-5.2	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%
GPT-4.1	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%
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%
DeepSeek-V2 Chat	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-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	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%
Llama 3.1 8B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	89	97.8%
GPT-4o Mini (temp=0)	100	100	100	100	88	97.7%
Gemini 3.1 Pro (Preview)	100	100	100	100	84	96.8%
DeepSeek V3.2	100	100	100	90	87	95.5%
Mistral Large 2	100	100	100	94	80	94.8%
MoonshotAI: Kimi K2.5	100	100	100	94	78	94.4%
Mistral Medium 3.1	100	100	100	100	69	93.9%
Claude 3.7 Sonnet	100	100	100	100	69	93.8%
Claude Sonnet 4.5	100	100	100	94	74	93.7%
Claude Sonnet 4	100	100	100	100	67	93.3%
Arcee AI: Trinity Mini	100	100	100	100	65	93.1%
DeepSeek V3 (2025-03-24)	100	100	100	100	61	92.2%
Llama 3.1 Nemotron 70B	100	100	100	100	57	91.3%
GPT-4o, May 13th (temp=0)	100	100	100	100	54	90.8%
Claude 3 Haiku	100	100	100	81	72	90.5%
Rocinante 12B	100	100	100	100	48	89.7%
Mistral Small 3.2 24B	100	100	100	100	44	88.7%
Hermes 3 405B	100	100	100	100	40	88.1%
GPT-4.1 Nano	100	100	100	100	35	87.1%
Qwen 2.5 72B	100	100	100	86	45	86.2%
Gemma 3 4B	100	100	88	73	66	85.3%
Gemini 2.5 Flash Lite	100	100	100	53	47	79.9%
Claude Opus 4	100	100	100	94	0	78.8%
GPT-4o, May 13th (temp=1)	100	100	100	94	0	78.7%
Z.AI GLM 4.5	100	100	100	92	0	78.4%
Gemma 3 12B	100	100	100	88	0	77.7%
Llama 3.1 70B	100	100	85	62	37	76.9%
Qwen 3.5 Plus (2026-02-15)	100	100	100	61	14	74.9%
DeepSeek V3.1	100	100	89	84	0	74.5%
Qwen 3.5 397B A17B	100	100	76	50	44	74.0%
Mistral NeMO	100	100	87	72	0	72.0%
Ministral 8B	100	74	71	56	55	71.3%
Mistral Large	100	79	72	46	45	68.4%
Mistral Small Creative	100	100	94	35	0	65.9%
Minimax M2.5	100	80	75	57	0	62.4%
Ministral 3 14B	87	77	69	47	31	62.4%
Gemini 3 Flash (Preview)	100	100	67	41	0	61.4%
Mistral Large 3	100	100	62	39	1	60.3%
Claude 3.5 Haiku	100	100	100	0	0	60.0%
Claude Sonnet 4.6	100	100	93	0	0	58.7%
Z.AI GLM 5	100	100	58	27	0	56.8%
Claude Opus 4.5	100	100	79	2	0	56.3%
Ministral 3 3B	100	100	72	0	0	54.4%
Ministral 3B	100	100	66	0	0	53.2%
Gemini 2.5 Flash	100	100	49	0	0	49.9%
Z.AI GLM 4.6	100	61	48	0	0	41.8%
Gemini 2.5 Pro	100	98	8	0	0	41.3%
Gemini 3 Pro (Preview)	100	50	37	9	0	39.2%
Claude Opus 4.6	91	74	30	0	0	39.1%
Ministral 3 8B	64	60	46	0	0	34.0%
Gemma 3 27B	100	54	5	0	0	31.9%
Z.AI GLM 4.7 Flash	67	57	25	0	0	29.8%
Z.AI GLM 4.7	83	35	27	0	0	29.1%
Claude Haiku 4.5	100	22	21	0	0	28.5%

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%
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%
GPT-5.2	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%
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%
GPT-4.1	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	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%
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-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%
Llama 3.1 70B	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	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%
Qwen 2.5 72B	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%
Llama 3.1 8B	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-4o, May 13th (temp=1)	100	100	100	100	99	99.8%
Claude Opus 4	100	100	100	100	97	99.5%
WizardLM 2 8x22b	100	100	100	100	92	98.5%
Minimax M2.5	100	100	100	100	91	98.1%
GPT-4o, May 13th (temp=0)	100	100	100	100	91	98.1%
Mistral Small Creative	100	100	100	100	87	97.3%
Ministral 3 14B	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	95	76	94.2%
DeepSeek V3.1	100	100	100	100	65	93.0%
Gemini 3 Pro (Preview)	100	100	100	100	64	92.9%
Ministral 3 3B	100	100	100	100	60	91.9%
Gemini 2.5 Pro	100	100	100	100	55	91.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	52	90.4%
Claude Opus 4.6	100	100	96	87	61	89.0%
Claude Opus 4.5	100	100	100	100	44	88.8%
Claude Haiku 4.5	100	100	100	100	36	87.3%
Z.AI GLM 4.6	100	100	100	100	28	85.6%
Gemma 3 12B	100	100	100	100	25	84.9%
Claude Sonnet 4.6	100	100	100	100	11	82.2%
Llama 3.1 Nemotron 70B	100	100	100	100	0	80.0%
Mistral Small 3.2 24B	100	100	100	100	0	80.0%
Claude 3.5 Haiku	100	100	100	96	0	79.2%
Z.AI GLM 4.7 Flash	100	100	52	0	0	50.4%

▼

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%
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%
GPT-5.2	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%
GPT-4.1	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%
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=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%
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%
Mistral Small Creative	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%
Arcee AI: Trinity Mini	100	100	100	100	100	100.0%
Llama 3.1 8B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	96	99.2%
Claude Sonnet 4.6	100	100	100	100	86	97.1%
Gemini 2.5 Flash Lite	100	100	100	97	88	97.0%
Mistral Large	100	100	100	100	85	97.0%
Mistral NeMO	100	100	100	100	83	96.5%
Claude 3.5 Sonnet	100	100	100	100	82	96.4%
Gemini 3 Pro (Preview)	100	100	100	100	80	96.0%
Gemma 3 12B	100	100	100	100	74	94.8%
Claude Opus 4.6	100	100	100	99	60	91.9%
Hermes 3 405B	100	100	100	100	58	91.6%
Llama 3.1 70B	100	100	100	95	62	91.4%
Ministral 3 8B	100	100	100	100	53	90.7%
Gemini 2.5 Pro	100	100	100	100	50	90.0%
Rocinante 12B	100	100	100	89	58	89.4%
Llama 3.1 Nemotron 70B	100	100	100	81	63	88.7%
DeepSeek-V2 Chat	100	100	100	73	69	88.5%
GPT-4.1 Nano	100	100	100	85	50	87.0%
Claude Haiku 4.5	100	100	100	68	52	84.0%
Ministral 3 3B	100	100	100	100	7	81.4%
Mistral Small 3.2 24B	100	100	100	100	0	80.0%
Ministral 3B	100	100	100	99	0	79.8%
ByteDance Seed 1.6	100	100	100	73	21	78.9%
Claude Opus 4	100	100	100	79	12	78.1%
Claude 3 Haiku	100	87	73	70	60	78.0%
DeepSeek V3 (2024-12-26)	100	100	100	84	0	76.7%
Claude Opus 4.5	100	100	100	50	32	76.5%
Qwen 2.5 72B	100	100	100	80	0	76.0%
Z.AI GLM 5	100	100	80	60	32	74.3%
Ministral 3 14B	100	100	100	63	0	72.5%
Z.AI GLM 4.7 Flash	100	100	81	80	0	72.2%
Gemma 3 27B	100	100	100	50	0	69.9%
Gemini 3 Flash (Preview)	100	100	73	68	0	68.3%
Gemma 3 4B	100	100	100	34	0	66.8%
Z.AI GLM 4.6	100	87	63	61	11	64.3%
WizardLM 2 8x22b	100	86	86	38	7	63.2%
DeepSeek V3.2	100	66	64	48	24	60.4%
Minimax M2.5	100	100	75	0	0	55.0%
DeepSeek V3.1	100	77	66	7	0	50.0%
Claude 3.5 Haiku	100	100	29	0	0	45.8%
Z.AI GLM 4.7	100	67	0	0	0	33.3%

▼

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-5.1	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%
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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
GPT-4.1	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%
Grok 4 Fast	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	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%
GPT-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	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%
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%
Qwen 2.5 72B	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%
Llama 3.1 8B	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%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	98	99.7%
GPT-5 Mini	100	100	100	100	96	99.2%
Cohere Command R+ (Aug. 2024)	100	100	100	100	92	98.5%
Z.AI GLM 4.7 Flash	100	100	100	100	87	97.4%
DeepSeek V3 (2025-03-24)	100	100	100	100	85	97.0%
Claude Opus 4.6	100	100	100	100	82	96.4%
Gemma 3 4B	100	100	100	100	68	93.5%
Mistral Small 3.2 24B	100	100	100	100	61	92.2%
Claude Haiku 4.5	100	100	100	82	78	92.1%
Z.AI GLM 5	100	100	100	100	60	91.9%
Gemini 3 Flash (Preview)	100	100	100	84	60	88.8%
DeepSeek V3.1	100	100	100	100	44	88.8%
Ministral 3 8B	100	100	100	98	40	87.6%
Mistral Small Creative	100	100	100	98	36	86.8%
Gemma 3 27B	100	100	100	66	61	85.4%
Claude Sonnet 4.5	100	100	100	100	25	84.9%
Minimax M2.5	100	100	100	99	20	83.9%
DeepSeek V3 (2024-12-26)	100	100	100	100	7	81.4%
Mistral Large 3	100	100	100	100	0	80.0%
Ministral 3 3B	100	100	100	100	0	80.0%
Mistral Large	100	100	100	77	17	78.9%
Mistral Large 2	100	100	100	87	0	77.4%
Ministral 3 14B	100	100	100	73	11	76.6%
Gemini 2.5 Pro	100	100	100	64	19	76.6%
Mistral Medium 3.1	100	100	100	38	35	74.8%
Claude 3.5 Haiku	100	100	100	37	15	70.4%
Ministral 3B	100	100	100	38	0	67.7%
Ministral 8B	100	100	100	0	0	60.0%
Z.AI GLM 4.6	100	100	81	0	0	56.2%
Claude Sonnet 4.6	100	54	41	0	0	39.1%

▼

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%
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%
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%
GPT-4.1	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%
DeepSeek-V2 Chat	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=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%
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%
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%
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%
Llama 3.1 8B	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	93	98.7%
Qwen 2.5 72B	100	100	100	100	82	96.4%
Cohere Command R+ (Aug. 2024)	100	100	100	100	82	96.4%
Claude Opus 4.6	100	100	100	100	81	96.3%
Arcee AI: Trinity Mini	100	100	100	100	79	95.8%
Claude Haiku 4.5	100	100	100	100	71	94.2%
Ministral 3 14B	100	100	100	100	69	93.9%
Gemma 3 4B	100	100	100	100	67	93.3%
WizardLM 2 8x22b	100	100	100	98	65	92.7%
Gemini 2.5 Pro	100	100	100	100	60	92.0%
Llama 3.1 70B	100	100	100	100	58	91.6%
Mistral Small 3.2 24B	100	100	100	100	58	91.6%
Gemini 3 Flash (Preview)	100	100	100	91	66	91.4%
Writer: Palmyra X5	100	100	100	92	61	90.5%
Rocinante 12B	100	100	100	100	30	86.0%
Gemini 3 Pro (Preview)	100	100	100	100	25	85.1%
Arcee AI: Trinity Large (Preview)	100	100	100	100	25	84.9%
GPT-4.1 Nano	100	100	100	100	23	84.7%
ByteDance Seed 1.6	100	100	100	100	20	84.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	12	82.4%
Gemma 3 12B	100	100	100	100	0	80.0%
Mistral Small Creative	100	100	100	100	0	80.0%
Hermes 3 405B	100	100	100	64	25	77.7%
Z.AI GLM 4.7	100	100	84	76	26	77.2%
Ministral 3B	100	100	87	74	17	75.7%
Mistral Large 3	100	100	84	78	0	72.3%
Mistral NeMO	100	93	89	57	0	67.9%
DeepSeek V3.1	100	84	81	55	0	64.0%
DeepSeek V3.2	100	100	72	14	0	57.1%
Z.AI GLM 4.6	100	100	81	0	0	56.2%
Z.AI GLM 4.7 Flash	32	0	0	0	0	6.3%

▼

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%
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%
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%
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%
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%
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%
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%
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%
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%
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%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100.0%
Rocinante 12B	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	93	98.7%
Z.AI GLM 4.5	100	100	100	100	89	97.8%
MoonshotAI: Kimi K2.5	100	100	100	100	86	97.1%
Z.AI GLM 4.7	100	100	100	100	86	97.1%
Claude Opus 4	100	100	100	100	84	96.9%
Z.AI GLM 4.7 Flash	100	100	100	100	84	96.9%
Mistral Medium 3.1	100	100	100	100	83	96.6%
Arcee AI: Trinity Mini	100	100	100	100	83	96.6%
Ministral 3 3B	100	100	100	100	76	95.3%
Claude Opus 4.6	100	100	100	100	75	95.1%
Claude Sonnet 4	100	100	100	100	73	94.6%
DeepSeek V3 (2024-12-26)	100	100	100	88	82	94.1%
Gemini 3 Pro (Preview)	100	100	100	100	64	92.9%
GPT-4.1 Nano	100	100	100	100	63	92.5%
Ministral 8B	100	100	100	100	57	91.4%
Claude Opus 4.5	100	100	100	100	37	87.5%
Mistral Small Creative	100	100	100	89	45	86.8%
Minimax M2.5	100	100	93	72	68	86.5%
Claude Haiku 4.5	100	100	100	100	20	84.0%
Ministral 3B	100	100	100	88	25	82.6%
Gemini 3 Flash (Preview)	100	100	100	100	6	81.2%
Ministral 3 14B	100	100	100	100	6	81.2%
Claude 3.5 Haiku	100	100	100	100	0	80.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	0	80.0%
Mistral NeMO	100	100	100	100	0	80.0%
DeepSeek V3.1	100	100	98	57	31	77.1%
Llama 3.1 8B	100	100	100	58	20	75.6%
Claude Sonnet 4.6	100	94	48	0	0	48.5%

▼

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%
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%
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%
Grok 4.1 Fast	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100.0%
GPT-4.1	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%
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-4.1 Mini	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	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%
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%
Gemini 2.5 Flash Lite	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	96	99.3%
Z.AI GLM 5	100	100	100	100	88	97.5%
Claude Sonnet 4.5	100	100	100	100	82	96.3%
Claude 3 Haiku	100	100	100	100	81	96.2%
Claude Opus 4.6	100	100	100	100	81	96.1%
Claude Opus 4	100	100	100	100	80	96.0%
Rocinante 12B	100	100	100	100	75	95.1%
Claude Sonnet 4	100	100	100	100	75	95.0%
Claude 3.5 Sonnet	100	100	100	100	74	94.8%
DeepSeek V3.1	100	100	100	100	68	93.7%
GPT-4.1 Nano	100	100	100	100	67	93.3%
Llama 3.1 8B	100	100	100	85	81	93.2%
GPT-4o, May 13th (temp=1)	100	100	100	100	64	92.8%
Hermes 3 405B	100	100	100	100	56	91.2%
Arcee AI: Trinity Mini	100	100	100	83	68	90.2%
Mistral Large 2	100	100	100	100	45	89.0%
Qwen 2.5 72B	100	100	100	100	43	88.6%
Z.AI GLM 4.7	100	98	84	81	80	88.6%
Claude Haiku 4.5	100	100	100	100	42	88.4%
Gemini 3 Pro (Preview)	100	100	100	89	46	86.8%
Claude Opus 4.5	100	100	86	74	67	85.5%
Mistral Large 3	100	100	100	94	32	85.2%
Mistral Medium 3.1	100	100	100	100	25	85.1%
Mistral NeMO	100	88	87	85	58	83.7%
Z.AI GLM 4.6	100	100	100	100	17	83.4%
Gemini 2.5 Pro	100	86	84	82	61	82.7%
Gemma 3 4B	100	100	100	59	53	82.5%
DeepSeek V3.2	100	100	100	79	32	82.2%
Ministral 8B	100	100	100	89	22	82.1%
Claude 3.5 Haiku	100	100	100	100	4	80.8%
Mistral Large	100	100	100	87	17	80.7%
Claude 3.7 Sonnet	100	100	100	100	0	80.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	0	80.0%
Ministral 3 8B	100	100	100	93	0	78.7%
Hermes 3 70B	100	100	100	61	27	77.7%
Z.AI GLM 4.7 Flash	100	100	100	88	0	77.5%
Claude Sonnet 4.6	100	100	77	66	30	74.5%
Z.AI GLM 4.5	100	100	100	50	17	73.4%
Gemini 3 Flash (Preview)	100	100	82	62	12	71.4%
WizardLM 2 8x22b	100	100	82	71	0	70.6%
Mistral Small Creative	100	100	74	40	20	66.9%
Mistral Small 3.2 24B	100	100	100	30	0	66.0%
Llama 3.1 70B	100	100	97	29	0	65.3%
Ministral 3 14B	100	100	100	0	0	60.0%

Past progressive (was/were + -ing) overuse

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