Structural similarity to original

Test: Text Replacement

Avg. Score

98.1%

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	Gemini 2.5 Flash Lite	100.0%	$0.0003	2.0s	100%
2	Ministral 8B	100.0%	$0.0001	3.6s	100%
3	Ministral 3 8B	100.0%	$0.0002	3.6s	100%
4	Mistral Small Creative	100.0%	$0.0003	3.6s	100%
5	GPT-4.1 Nano	100.0%	$0.0003	4.4s	100%
6	Ministral 3 14B	100.0%	$0.0003	4.8s	100%
7	Mistral Small 3.2 24B	100.0%	$0.0003	6.2s	100%
8	Gemini 2.5 Flash	100.0%	$0.0018	2.5s	100%
9	Gemma 3 4B	100.0%	$0.0001	8.0s	100%
10	Mistral Medium 3.1	100.0%	$0.0015	5.6s	100%
11	Gemini 3 Flash (Preview)	100.0%	$0.0022	3.9s	100%
12	Gemma 3 12B	100.0%	$0.0001	10.4s	100%
13	Grok 4 Fast	100.0%	$0.0011	8.7s	100%
14	GPT-4.1 Mini	100.0%	$0.0013	8.3s	100%
15	GPT-4o Mini (temp=1)	100.0%	$0.0005	10.7s	100%
16	Mistral Large 3	100.0%	$0.0013	8.8s	100%
17	GPT-4o Mini (temp=0)	100.0%	$0.0005	11.6s	100%
18	Qwen 3.5 Plus (2026-02-15)	100.0%	$0.0018	8.7s	100%
19	Qwen 2.5 72B	100.0%	$0.0003	13.2s	100%
20	Claude Haiku 4.5	100.0%	$0.0042	4.2s	100%
21	Gemma 3 27B	100.0%	$0.0002	19.8s	100%
22	GPT-4.1	100.0%	$0.0064	5.3s	100%
23	Writer: Palmyra X5	100.0%	$0.0042	11.0s	100%
24	Mistral Large	100.0%	$0.0052	8.7s	100%
25	Mistral Large 2	100.0%	$0.0052	8.8s	100%
26	Grok 4.1 Fast	100.0%	$0.0014	18.6s	100%
27	Arcee AI: Trinity Large (Preview)	100.0%	$0.0000	27.1s	100%
28	Gemini 2.5 Flash Lite (Reasoning)	100.0%	$0.0022	21.7s	100%
29	Hermes 3 405B	100.0%	$0.0014	27.5s	100%
30	GPT-4o, May 13th (temp=0)	100.0%	$0.013	3.6s	100%
31	GPT-4o, May 13th (temp=1)	100.0%	$0.013	4.0s	100%
32	Claude Sonnet 4.6	100.0%	$0.013	6.0s	100%
33	Claude Sonnet 4.5	100.0%	$0.013	5.9s	100%
34	Claude 3.7 Sonnet	100.0%	$0.013	7.2s	100%
35	Gemini 2.5 Flash (Reasoning)	100.0%	$0.0096	15.1s	100%
36	Claude Sonnet 4	100.0%	$0.013	7.4s	100%
37	DeepSeek V3.2	100.0%	$0.0005	49.1s	100%
38	GPT-5.2	100.0%	$0.016	13.8s	100%
39	GPT-5 Mini	100.0%	$0.0064	39.1s	100%
40	Claude Opus 4.5	100.0%	$0.021	6.7s	100%
41	Claude Opus 4.6	100.0%	$0.021	7.1s	100%
42	Z.AI GLM 4.6	100.0%	$0.0059	46.8s	100%
43	Minimax M2.5	100.0%	$0.0019	57.8s	100%
44	GPT-5.1	100.0%	$0.019	21.1s	100%
45	DeepSeek V3 (2024-12-26)	98.8%	$0.0010	19.4s	88%
46	Claude 3.5 Sonnet	100.0%	$0.025	11.8s	100%
47	Gemini 3 Flash (Preview, Reasoning)	100.0%	$0.018	30.3s	100%
48	Ministral 3B	97.6%	$0.0001	2.3s	83%
49	ByteDance Seed 1.6	100.0%	$0.0057	1.0m	100%
50	DeepSeek V3 (2025-03-24)	98.8%	$0.0007	41.6s	88%
51	ByteDance Seed 1.6 Flash	97.6%	$0.0009	16.8s	83%
52	DeepSeek-V2 Chat	97.6%	$0.0009	18.8s	83%
53	Z.AI GLM 4.5	98.8%	$0.0045	36.8s	88%
54	Ministral 3 3B	96.4%	$0.0001	2.4s	79%
55	Llama 3.1 70B	97.6%	$0.0006	24.7s	83%
56	Grok 4	100.0%	$0.030	36.9s	100%
57	GPT-5	100.0%	$0.035	51.8s	100%
58	Llama 3.1 Nemotron 70B	95.0%	$0.0017	18.0s	76%
59	Llama 3.1 8B	94.0%	$0.0001	10.7s	74%
60	Gemini 2.5 Pro	100.0%	$0.046	34.9s	100%
61	DeepSeek V3.1	95.2%	$0.0008	35.6s	77%
62	o4 Mini	97.6%	$0.019	30.0s	83%
63	Mistral NeMO	93.2%	$0.0002	3.1s	70%
64	Cohere Command R+ (Aug. 2024)	95.4%	$0.0079	25.9s	78%
65	Gemini 3 Pro (Preview)	100.0%	$0.049	33.0s	100%
66	GPT-4o, Aug. 6th (temp=0)	96.4%	$0.0078	3.2s	63%
67	Claude Opus 4	100.0%	$0.063	10.6s	100%
68	Z.AI GLM 5	100.0%	$0.016	2.2m	100%
69	Z.AI GLM 4.7	100.0%	$0.011	2.5m	100%
70	GPT-5 Nano	95.2%	$0.0035	1.3m	77%
71	o4 Mini High	98.8%	$0.039	58.8s	88%
72	Qwen 3.5 397B A17B	100.0%	$0.010	3.1m	100%
73	Z.AI GLM 4.7 Flash	96.4%	$0.0024	2.0m	79%
74	Claude Sonnet 4.6 (Reasoning)	100.0%	$0.071	50.0s	100%
75	Claude Opus 4.6 (Reasoning)	100.0%	$0.076	37.6s	100%
76	GPT-4o, Aug. 6th (temp=1)	92.9%	$0.0075	3.4s	48%
77	Aion 2.0	95.2%	$0.0056	1.2m	61%
78	WizardLM 2 8x22b	93.1%	$0.0010	1.1m	50%
79	Arcee AI: Trinity Mini	85.7%	$0.0006	23.0s	55%
80	Gemini 3.1 Pro (Preview)	100.0%	$0.099	1.5m	100%
81	MoonshotAI: Kimi K2.5	98.8%	$0.020	4.2m	88%
82	Claude 3 Haiku	81.0%	$0.0011	5.5s	42%
83	Rocinante 12B	72.8%	$0.0004	8.8s	34%
84	Hermes 3 70B	78.6%	$0.0014	1.8m	18%
98.08%

Individual Scenarios

Generic Prompt

▼

Avoid said/asked/replied/answered

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100	100	100.0%
Aion 2.0	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash (Reasoning)	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100	100	100.0%
Llama 3.1 8B	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100	67	95.2%
DeepSeek V3.1	100	100	100	100	100	100	67	95.2%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100	67	95.2%
Ministral 3B	100	100	100	100	100	100	67	95.2%
Llama 3.1 Nemotron 70B	100	100	100	100	100	67	61	89.7%
Claude 3 Haiku	100	100	67	67	67	67	36	71.7%
Arcee AI: Trinity Mini	67	67	67	67	67	67	67	66.7%
Rocinante 12B	67	67	67	67	67	51	0	55.0%

▼

Passive voice → active voice

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100	100	100.0%
Aion 2.0	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash (Reasoning)	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100	100	100.0%
Hermes 3 70B	100	100	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	97	94	92	97.5%
o4 Mini High	100	100	100	100	100	100	67	95.2%
DeepSeek V3.1	100	100	100	100	100	100	67	95.2%
o4 Mini	100	100	100	100	100	67	67	90.5%
Llama 3.1 8B	100	100	100	100	100	67	67	90.5%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100	0	85.7%
GPT-5 Nano	100	100	100	100	67	67	67	85.7%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100	0	85.7%
Rocinante 12B	100	100	100	85	64	54	45	78.3%
Mistral NeMO	100	100	100	67	67	58	52	77.6%
WizardLM 2 8x22b	100	100	100	100	100	7	0	72.5%
Claude 3 Haiku	67	67	67	67	67	67	67	66.7%

Specific Prompt

▼

Avoid said/asked/replied/answered

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash (Reasoning)	100	100	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100	100	100.0%
DeepSeek-V2 Chat	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100	100	100.0%
Ministral 3 3B	100	100	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100	100	100.0%
Ministral 3B	100	100	100	100	100	100	100	100.0%
DeepSeek V3.1	100	100	100	100	100	100	67	95.2%
Mistral NeMO	100	100	100	100	100	100	67	95.2%
Llama 3.1 8B	100	100	100	100	100	100	67	95.2%
Aion 2.0	100	100	100	100	100	100	67	95.2%
Z.AI GLM 4.5	100	100	100	100	100	100	67	95.2%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	67	95.2%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100	67	95.2%
Llama 3.1 70B	100	100	100	100	100	67	67	90.5%
Llama 3.1 Nemotron 70B	100	100	100	100	100	67	67	90.5%
Hermes 3 70B	100	100	100	100	100	100	0	85.7%
Claude 3 Haiku	100	100	100	100	67	67	67	85.7%
Cohere Command R+ (Aug. 2024)	100	100	100	97	67	64	61	84.1%
Arcee AI: Trinity Mini	100	100	100	100	67	67	0	76.2%
Rocinante 12B	95	67	67	67	65	39	38	62.6%

▼

Passive voice → active voice

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100.0%
Claude Opus 4.6	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100.0%
Claude Opus 4.5	100	100	100	100	100	100	100	100.0%
Grok 4.1 Fast	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.6	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4	100	100	100	100	100	100	100	100.0%
Minimax M2.5	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100.0%
GPT-4.1	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Pro	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100.0%
Grok 4	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.5	100	100	100	100	100	100	100	100.0%
Claude Opus 4	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash (Reasoning)	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.5	100	100	100	100	100	100	100	100.0%
Grok 4 Fast	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Plus (2026-02-15)	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	100	100	100	100	100.0%
Mistral Large 3	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100.0%
Claude Haiku 4.5	100	100	100	100	100	100	100	100.0%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	100	100.0%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	100	100.0%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100.0%
GPT-4.1 Mini	100	100	100	100	100	100	100	100.0%
Hermes 3 405B	100	100	100	100	100	100	100	100.0%
GPT-4o, Aug. 6th (temp=0)	100	100	100	100	100	100	100	100.0%
Mistral Large 2	100	100	100	100	100	100	100	100.0%
DeepSeek V3.2	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash Lite	100	100	100	100	100	100	100	100.0%
Gemini 2.5 Flash	100	100	100	100	100	100	100	100.0%
Mistral Large	100	100	100	100	100	100	100	100.0%
Writer: Palmyra X5	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	100	100.0%
Mistral Small 3.2 24B	100	100	100	100	100	100	100	100.0%
Gemma 3 12B	100	100	100	100	100	100	100	100.0%
Llama 3.1 70B	100	100	100	100	100	100	100	100.0%
GPT-4o Mini (temp=0)	100	100	100	100	100	100	100	100.0%
Gemma 3 27B	100	100	100	100	100	100	100	100.0%
Mistral Medium 3.1	100	100	100	100	100	100	100	100.0%
Qwen 2.5 72B	100	100	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Large (Preview)	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100	100	100.0%
Mistral Small Creative	100	100	100	100	100	100	100	100.0%
Ministral 3 14B	100	100	100	100	100	100	100	100.0%
GPT-4.1 Nano	100	100	100	100	100	100	100	100.0%
Ministral 3 8B	100	100	100	100	100	100	100	100.0%
Claude 3 Haiku	100	100	100	100	100	100	100	100.0%
WizardLM 2 8x22b	100	100	100	100	100	100	100	100.0%
Arcee AI: Trinity Mini	100	100	100	100	100	100	100	100.0%
Cohere Command R+ (Aug. 2024)	100	100	100	100	100	100	100	100.0%
Gemma 3 4B	100	100	100	100	100	100	100	100.0%
Mistral NeMO	100	100	100	100	100	100	100	100.0%
Ministral 8B	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	67	95.2%
GPT-5 Nano	100	100	100	100	100	100	67	95.2%
DeepSeek V3.1	100	100	100	100	100	100	67	95.2%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	100	67	95.2%
Ministral 3B	100	100	100	100	100	100	67	95.2%
Rocinante 12B	100	100	100	100	100	100	67	95.2%
DeepSeek-V2 Chat	100	100	100	100	100	67	67	90.5%
Z.AI GLM 4.7 Flash	100	100	100	100	100	67	67	90.5%
Llama 3.1 8B	100	100	100	100	100	67	67	90.5%
Aion 2.0	100	100	100	100	100	100	0	85.7%
GPT-4o, Aug. 6th (temp=1)	100	100	100	100	100	100	0	85.7%
Ministral 3 3B	100	100	100	100	67	67	67	85.7%
Hermes 3 70B	100	100	0	0	0	0	0	28.6%

Structural similarity to original

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

Generic Prompt

Avoid said/asked/replied/answered

Passive voice → active voice

Specific Prompt

Avoid said/asked/replied/answered

Passive voice → active voice