Matches word count

Test: N-Length Sentences

Avg. Score

76.6%

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	Gemini 3.1 Flash Lite (Preview)	100.0%	$0.0001	1.2s	100%
2	Inception Mercury 2	99.9%	$0.0007	1.2s	98%
3	GPT-5.4 Nano (Reasoning)	100.0%	$0.0010	7.5s	100%
4	GPT-5.4 Mini (Reasoning, Low)	100.0%	$0.0025	6.3s	100%
5	Gemini 3 Flash (Preview)	99.2%	$0.0004	1.9s	95%
6	Nemotron 3 Super	100.0%	$0.0000	16.0s	100%
7	GPT-5.4 Mini (Reasoning)	100.0%	$0.0038	8.1s	100%
8	GPT-5.4 Nano (Reasoning, Low)	99.5%	$0.0008	5.7s	95%
9	Inception Mercury	98.0%	$0.0001	1.6s	90%
10	GPT-5 Nano	100.0%	$0.0010	28.2s	100%
11	Stealth: Aurora Alpha	98.5%	—	1.7s	90%
12	GPT-5.4 (Reasoning, Low)	100.0%	$0.0093	10.4s	100%
13	o4 Mini	100.0%	$0.0083	20.8s	100%
14	GPT-5.2	100.0%	$0.011	15.0s	100%
15	Gemini 3 Flash (Preview, Reasoning)	100.0%	$0.010	17.7s	100%
16	Qwen 3.5 Flash	100.0%	$0.0024	38.6s	100%
17	GPT-5 Mini	99.3%	$0.0043	26.2s	94%
18	Z.AI GLM 5 Turbo	100.0%	$0.011	26.6s	100%
19	GPT-5.4 (Reasoning)	99.8%	$0.013	19.5s	98%
20	o4 Mini High	100.0%	$0.011	27.6s	100%
21	Grok 4.20 (Beta, Reasoning)	99.1%	$0.014	8.0s	92%
22	MiniMax M2.5	98.8%	$0.0031	39.2s	90%
23	MiniMax M2.7	98.9%	$0.0041	44.4s	93%
24	Gemini 3 Pro (Preview)	99.1%	$0.018	13.0s	93%
25	GPT-5.1	99.7%	$0.017	26.6s	97%
26	Claude Opus 4.5	93.6%	$0.0052	6.8s	79%
27	Qwen 3.5 35B	99.7%	$0.013	39.4s	96%
28	ByteDance Seed 2.0 Lite	99.3%	$0.0051	58.7s	96%
29	MoonshotAI: Kimi K2.5	99.8%	$0.0086	55.1s	98%
30	GPT-5.4 Mini	88.4%	$0.0006	1.1s	71%
31	GPT-4.1	88.1%	$0.0012	2.8s	73%
32	GPT-4o Mini (temp=0)	86.1%	$0.0001	9.2s	69%
33	Mistral Small 4 (Reasoning)	90.4%	$0.0015	16.7s	70%
34	Qwen 3.5 27B	100.0%	$0.016	1.0m	100%
35	Aion 2.0	96.6%	$0.0034	50.7s	82%
36	ByteDance Seed 1.6	95.8%	$0.0027	31.1s	71%
37	GPT-5.4	86.7%	$0.0019	4.4s	63%
38	GPT-4o, May 13th (temp=0)	86.9%	$0.0025	4.6s	61%
39	Qwen 3.5 122B	100.0%	$0.026	57.1s	100%
40	Llama 3.1 70B	83.6%	$0.0002	2.1s	56%
41	ByteDance Seed 1.6 Flash	87.4%	$0.0007	13.5s	57%
42	GPT-4o Mini (temp=1)	84.5%	$0.0001	6.1s	56%
43	Qwen 3.5 9B	100.0%	$0.0013	2.1m	100%
44	GPT-5	99.9%	$0.031	51.9s	99%
45	Mistral Medium 3.1	81.0%	$0.0003	4.3s	54%
46	Claude Opus 4	87.2%	$0.015	13.2s	66%
47	Z.AI GLM 4.7 Flash	91.7%	$0.0018	1.3m	77%
48	Claude Opus 4.6	83.8%	$0.0055	7.6s	53%
49	GPT-4.1 Nano	77.8%	$0.0001	2.4s	50%
50	Z.AI GLM 5	98.5%	$0.011	1.6m	89%
51	Llama 3.1 Nemotron 70B	81.2%	$0.0001	5.7s	47%
52	GPT-4o, May 13th (temp=1)	80.5%	$0.0021	4.7s	49%
53	GPT-4.1 Mini	79.6%	$0.0002	2.2s	45%
54	Grok 4	82.8%	$0.0072	15.0s	56%
55	Claude Opus 4.6 (Reasoning)	99.8%	$0.052	27.5s	98%
56	Claude Sonnet 4.5	81.9%	$0.0033	6.0s	46%
57	Claude 3.5 Haiku	79.9%	$0.0006	2.5s	41%
58	Llama 3.1 8B	79.5%	$0.0000	910ms	39%
59	Nemotron 3 Nano	99.7%	$0.0023	2.5m	97%
60	Gemini 3.1 Pro (Preview)	100.0%	$0.051	43.9s	100%
61	Claude Sonnet 4	79.0%	$0.0029	5.2s	40%
62	Qwen 2.5 72B	77.4%	$0.0003	16.6s	44%
63	Gemini 2.5 Pro	85.2%	$0.018	16.6s	57%
64	ByteDance Seed 2.0 Mini	99.5%	$0.0026	2.7m	98%
65	Claude 3.7 Sonnet	77.0%	$0.0032	5.1s	41%
66	Stealth: Healer Alpha	79.4%	$0.0000	12.1s	36%
67	GPT-4o, Aug. 6th (temp=1)	74.4%	$0.0015	2.4s	35%
68	Gemma 3 27B	72.9%	$0.0000	5.4s	31%
69	Ministral 3 14B	65.9%	$0.0001	2.0s	37%
70	Gemini 2.5 Flash Lite (Reasoning)	70.0%	$0.0005	5.6s	34%
71	DeepSeek V3 (2025-03-24)	70.2%	$0.0001	6.9s	28%
72	Qwen3 235B A22B Instruct 2507	66.5%	$0.0001	6.9s	32%
73	Claude 3.5 Sonnet	71.3%	$0.0028	4.6s	28%
74	Claude Haiku 4.5	67.1%	$0.0009	2.9s	28%
75	Claude Sonnet 4.6	70.1%	$0.0024	4.6s	25%
76	Grok 4.1 Fast	69.6%	$0.0006	10.7s	25%
77	GPT-4o, Aug. 6th (temp=0)	67.5%	$0.0013	2.2s	23%
78	DeepSeek V3 (2024-12-26)	65.5%	$0.0002	6.6s	26%
79	Writer: Palmyra X5	62.2%	$0.0014	7.9s	32%
80	Mistral Small Creative	57.8%	$0.0001	1.2s	32%
81	Claude Sonnet 4.6 (Reasoning)	100.0%	$0.078	49.2s	100%
82	Z.AI GLM 4.7	95.1%	$0.0065	2.5m	71%
83	Stealth: Hunter Alpha	67.2%	$0.0000	16.6s	24%
84	Mistral Small 4	58.1%	$0.0001	1.6s	23%
85	Qwen 3.5 397B A17B	100.0%	$0.025	3.0m	100%
86	GPT-5.4 Nano	58.0%	$0.0002	1.4s	20%
87	Gemma 3 12B	62.9%	$0.0000	4.1s	15%
88	Gemini 2.5 Flash (Reasoning)	64.0%	$0.0038	7.4s	20%
89	Mistral Small 3.2 24B	54.7%	$0.0001	2.6s	22%
90	Grok 4.20 (Beta)	58.4%	$0.0006	898ms	17%
91	Grok 4 Fast	53.1%	$0.0003	4.0s	22%
92	Gemma 3 4B	57.3%	$0.0000	1.8s	15%
93	Hermes 3 405B	58.2%	$0.0000	11.9s	18%
94	Mistral Large 3	56.9%	$0.0003	4.6s	16%
95	Qwen 3.5 Plus (2026-02-15)	52.4%	$0.0003	5.9s	20%
96	Gemini 2.5 Flash Lite	51.9%	$0.0000	785ms	16%
97	Claude 3 Haiku	48.5%	$0.0002	2.7s	20%
98	LFM2 24B	51.5%	$0.0000	3.1s	15%
99	DeepSeek V3.2	60.8%	$0.0003	16.5s	11%
100	DeepSeek V3.1	53.6%	$0.0001	9.1s	14%
101	Ministral 3 3B	41.8%	$0.0000	1.0s	21%
102	Cohere Command R+ (Aug. 2024)	44.8%	$0.0008	2.0s	17%
103	Arcee AI: Trinity Large (Preview)	42.9%	$0.0000	3.6s	18%
104	WizardLM 2 8x22b	43.7%	$0.0002	8.4s	19%
105	Gemini 2.5 Flash	44.0%	$0.0003	1.3s	12%
106	Ministral 3 8B	41.6%	$0.0000	1.5s	10%
107	Hermes 3 70B	42.1%	$0.0001	5.8s	11%
108	Qwen 3 32B	38.4%	$0.0003	13.8s	19%
109	Z.AI GLM 4.5	41.9%	$0.0003	5.8s	8%
110	Z.AI GLM 4.6	57.6%	$0.0034	55.9s	15%
111	Mistral Large 2	37.5%	$0.0007	2.9s	7%
112	Mistral Large	40.3%	$0.0037	5.3s	8%
113	Arcee AI: Trinity Mini	31.3%	$0.0001	3.2s	11%
114	Ministral 3B	26.1%	$0.0000	768ms	14%
115	Ministral 8B	28.4%	$0.0000	904ms	7%
116	DeepSeek-V2 Chat	33.3%	$0.0001	10.5s	3%
117	Rocinante 12B	27.0%	$0.0001	8.4s	9%
118	Mistral NeMO	18.6%	$0.0000	1.9s	7%
76.55%

Individual Scenarios

▼

Write sentences with 5 words each

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5 Turbo	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5 Mini	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 122B	100	100	100	100	100	100	100	100	100	100	100.0%
Grok 4.20 (Beta, Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 27B	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
MiniMax M2.5	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 35B	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Flash	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 9B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Nemotron 3 Super	100	100	100	100	100	100	100	100	100	100	100.0%
Inception Mercury 2	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Nano (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Nano (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Nemotron 3 Nano	100	100	100	100	100	100	100	100	100	100	100.0%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100	100	99	99.9%
Llama 3.1 70B	100	100	100	100	100	100	100	100	100	98	99.8%
Llama 3.1 8B	100	100	100	100	100	100	100	100	100	98	99.8%
Grok 4	100	100	100	100	100	100	100	100	100	98	99.8%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100	100	96	99.6%
Inception Mercury	100	100	100	100	100	100	100	100	100	95	99.5%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100	100	94	99.4%
GPT-4o, May 13th (temp=0)	100	100	100	100	100	100	100	98	98	98	99.3%
ByteDance Seed 2.0 Mini	100	100	100	100	100	100	100	98	98	97	99.3%
GPT-5.1	100	100	100	100	100	100	100	100	100	92	99.2%
Mistral Medium 3.1	100	100	100	100	100	100	98	98	97	97	99.0%
ByteDance Seed 2.0 Lite	100	100	100	100	100	100	100	100	98	92	98.9%
Claude Opus 4.5	100	100	100	100	100	100	100	100	100	89	98.9%
MiniMax M2.7	100	100	100	100	100	100	100	100	100	89	98.9%
Gemini 2.5 Pro	100	100	100	100	100	100	98	97	97	96	98.9%
GPT-4o, May 13th (temp=1)	100	100	100	100	100	100	98	97	96	96	98.7%
GPT-5.4 Mini	100	100	100	100	100	98	98	98	97	96	98.6%
GPT-4o Mini (temp=0)	100	98	98	98	98	98	98	98	98	96	98.3%
Gemini 2.5 Flash Lite (Reasoning)	100	100	100	99	98	98	98	97	97	96	98.3%
GPT-4.1 Mini	100	100	100	100	99	98	98	97	96	93	98.1%
Gemma 3 27B	100	100	100	100	100	98	98	96	96	93	98.0%
Claude Opus 4.6	100	100	100	100	100	100	98	95	94	93	97.9%
Stealth: Aurora Alpha	100	100	100	100	100	100	100	100	91	89	97.9%
GPT-4o Mini (temp=1)	100	100	100	100	100	100	96	95	94	93	97.8%
Claude Opus 4	100	100	100	100	100	100	97	95	94	93	97.8%
Claude 3.7 Sonnet	100	100	100	100	100	100	100	100	100	78	97.8%
Claude 3.5 Sonnet	100	100	100	100	100	100	100	96	93	87	97.6%
Gemini 2.5 Flash (Reasoning)	100	99	99	99	99	97	97	96	95	95	97.5%
GPT-5.4	100	100	100	100	100	100	98	96	91	89	97.5%
Aion 2.0	100	100	100	100	100	100	100	97	90	83	97.1%
GPT-4.1 Nano	100	100	100	100	100	98	97	96	91	89	97.1%
Mistral Small 4 (Reasoning)	100	100	100	100	98	97	96	94	94	91	96.9%
DeepSeek V3 (2025-03-24)	100	100	100	100	100	98	98	98	88	81	96.3%
Z.AI GLM 4.7 Flash	100	100	100	100	100	100	100	96	87	80	96.3%
Gemma 3 12B	100	100	100	98	96	96	96	96	93	87	96.0%
Z.AI GLM 4.6	100	98	98	98	97	96	94	93	92	90	95.7%
Claude Sonnet 4	100	100	100	100	97	97	93	92	91	86	95.6%
GPT-4o, Aug. 6th (temp=1)	100	100	99	99	96	95	94	93	91	89	95.5%
Claude Sonnet 4.5	100	100	100	100	99	96	94	91	89	86	95.5%
Gemma 3 4B	100	100	100	98	98	98	94	93	89	77	94.6%
DeepSeek V3 (2024-12-26)	100	100	100	100	100	100	96	93	86	70	94.5%
GPT-4o, Aug. 6th (temp=0)	98	96	96	94	93	93	93	93	93	92	94.2%
Claude 3.5 Haiku	100	98	98	96	92	92	91	91	91	91	93.9%
GPT-4.1	100	98	98	98	97	96	96	89	88	78	93.7%
DeepSeek V3.2	100	100	100	100	100	99	93	87	78	78	93.6%
Z.AI GLM 4.5	100	100	100	98	98	98	89	87	82	81	93.2%
DeepSeek V3.1	100	100	99	98	97	97	90	85	84	82	93.2%
Claude Haiku 4.5	99	99	99	98	97	92	90	88	86	84	93.1%
Qwen3 235B A22B Instruct 2507	99	98	94	93	93	92	91	90	86	80	91.6%
Mistral Large 3	96	93	93	93	91	91	89	89	89	89	91.4%
Mistral Small 4	100	96	96	96	93	92	91	87	82	76	90.8%
Gemini 2.5 Flash Lite	100	98	96	95	93	91	89	86	86	72	90.7%
LFM2 24B	93	92	92	92	91	91	89	89	89	85	90.2%
Grok 4.20 (Beta)	100	100	100	100	98	98	83	81	78	63	89.9%
Qwen 2.5 72B	100	100	100	100	100	100	100	95	93	0	88.9%
Stealth: Hunter Alpha	100	100	100	98	94	91	80	77	73	67	88.0%
ByteDance Seed 1.6 Flash	100	100	96	91	91	89	87	85	72	60	87.0%
Mistral Large	96	95	93	90	89	89	83	82	79	73	86.9%
DeepSeek-V2 Chat	100	93	91	89	89	82	82	80	78	72	85.6%
Ministral 3 14B	93	91	90	89	88	87	80	80	79	72	84.9%
Mistral Small 3.2 24B	95	93	91	90	87	85	83	80	77	63	84.6%
Gemini 2.5 Flash	98	98	95	93	93	92	88	84	64	40	84.3%
Hermes 3 70B	100	100	98	92	90	87	87	69	58	56	83.7%
Grok 4.1 Fast	100	99	91	80	78	78	78	78	78	78	83.7%
Hermes 3 405B	90	90	88	87	85	84	83	80	76	69	83.1%
Qwen 3.5 Plus (2026-02-15)	100	91	82	78	78	78	78	78	78	78	81.9%
GPT-5.4 Nano	89	87	85	78	78	78	78	75	72	70	78.9%
Writer: Palmyra X5	100	98	96	90	83	82	78	76	73	11	78.6%
Stealth: Healer Alpha	100	100	100	100	100	100	100	78	7	1	78.5%
Arcee AI: Trinity Large (Preview)	93	87	81	81	80	77	72	69	66	56	76.2%
Grok 4 Fast	89	78	78	78	78	78	70	70	67	53	73.8%
Mistral Small Creative	80	80	78	72	72	72	72	72	70	63	73.3%
Mistral Large 2	91	91	91	89	87	82	70	60	52	16	73.0%
Cohere Command R+ (Aug. 2024)	94	89	82	78	76	76	65	53	51	36	69.9%
Ministral 3 3B	93	84	74	74	64	63	56	56	52	50	66.5%
Claude 3 Haiku	89	85	81	78	72	72	68	65	47	1	65.8%
WizardLM 2 8x22b	91	89	89	85	81	68	64	50	23	10	65.0%
Ministral 8B	100	100	78	78	64	56	45	36	32	20	61.0%
Arcee AI: Trinity Mini	97	89	76	73	63	53	45	45	27	24	59.3%
Rocinante 12B	88	78	72	66	62	59	59	40	34	22	58.1%
Ministral 3 8B	96	93	90	85	55	36	34	9	7	7	51.1%
Ministral 3B	71	64	64	64	52	52	40	37	20	0	46.5%
Qwen 3 32B	90	84	67	54	34	29	22	13	1	0	39.5%
Mistral NeMO	72	47	45	37	35	22	21	17	1	1	29.8%

▼

Write sentences with 10 words each

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Avg ▼
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5 Turbo	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 122B	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 27B	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Flash	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 9B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Nemotron 3 Super	100	100	100	100	100	100	100	100	100	100	100.0%
Stealth: Aurora Alpha	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Nano (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Nano (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100	100	98	99.8%
GPT-5 Mini	100	100	100	100	100	100	100	100	100	97	99.7%
Claude Opus 4.5	100	100	100	100	100	100	100	100	100	97	99.7%
Inception Mercury 2	100	100	100	100	100	100	100	100	100	96	99.6%
ByteDance Seed 2.0 Lite	100	100	100	100	100	100	100	100	98	97	99.5%
Grok 4.20 (Beta, Reasoning)	100	100	100	100	100	100	100	100	100	95	99.5%
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100	98	94	99.3%
Inception Mercury	100	100	100	100	100	100	100	100	96	96	99.2%
Nemotron 3 Nano	100	100	100	100	100	100	100	100	100	91	99.1%
ByteDance Seed 2.0 Mini	100	100	100	100	100	100	100	97	97	97	99.1%
Qwen 3.5 35B	100	100	100	100	100	100	100	100	100	90	99.0%
Claude Opus 4	100	100	100	100	100	100	100	100	100	88	98.8%
MiniMax M2.5	100	100	100	100	100	100	100	100	100	88	98.8%
Aion 2.0	100	100	100	100	100	100	100	100	97	90	98.7%
Llama 3.1 Nemotron 70B	100	100	100	100	100	100	97	97	97	95	98.7%
MiniMax M2.7	100	100	100	100	100	100	100	100	89	89	97.8%
Z.AI GLM 5	100	100	100	100	100	100	100	100	100	74	97.4%
Claude Sonnet 4.5	100	100	100	100	100	100	98	97	90	87	97.2%
Claude 3.5 Haiku	100	100	100	100	100	98	95	95	94	90	97.1%
Llama 3.1 70B	100	100	100	100	100	100	97	95	87	84	96.4%
Llama 3.1 8B	100	100	100	100	97	96	95	95	91	77	95.1%
Claude Opus 4.6	100	100	100	100	100	100	99	98	76	74	94.7%
GPT-4o, Aug. 6th (temp=1)	100	97	95	95	95	95	95	95	90	90	94.6%
GPT-5.4	100	100	100	97	95	95	94	90	87	84	94.2%
Gemini 2.5 Pro	100	100	100	96	96	95	91	90	85	84	93.9%
GPT-4o, Aug. 6th (temp=0)	100	95	95	95	92	92	92	92	90	90	93.3%
Claude 3.7 Sonnet	100	96	95	94	94	93	93	93	91	81	93.1%
GPT-4o Mini (temp=1)	97	95	95	95	92	92	92	92	90	83	92.4%
GPT-4.1 Mini	97	97	95	92	92	92	91	90	88	84	92.0%
GPT-4.1	100	97	97	95	92	92	92	90	83	79	91.8%
Claude Sonnet 4	100	100	100	100	100	97	90	88	74	69	91.8%
Claude 3.5 Sonnet	100	100	97	95	92	92	90	86	83	78	91.3%
Grok 4.1 Fast	100	100	97	94	92	91	87	85	84	82	91.2%
Z.AI GLM 4.7	100	100	100	100	100	100	100	90	74	39	90.3%
Gemma 3 27B	95	92	92	92	92	90	90	87	84	83	89.7%
Z.AI GLM 4.7 Flash	100	100	100	100	96	96	79	77	74	74	89.7%
DeepSeek V3.2	100	100	97	95	95	90	90	90	72	59	88.8%
GPT-4o Mini (temp=0)	92	90	90	90	90	90	90	87	84	84	88.6%
GPT-4o, May 13th (temp=0)	97	97	97	97	92	92	87	87	70	63	88.2%
Hermes 3 405B	97	97	92	92	88	87	87	87	84	67	87.9%
ByteDance Seed 1.6	100	100	100	100	100	100	100	95	42	41	87.8%
Gemma 3 12B	95	92	92	90	90	87	87	85	84	74	87.6%
GPT-5.4 Nano	97	95	92	92	90	87	84	84	81	71	87.4%
GPT-5.4 Mini	94	94	93	91	89	89	87	86	85	65	87.3%
GPT-4o, May 13th (temp=1)	95	92	92	91	90	87	83	80	80	72	86.1%
Stealth: Hunter Alpha	100	100	99	93	92	90	90	90	49	32	83.4%
Qwen 2.5 72B	100	100	92	91	90	88	85	83	65	37	83.3%
Mistral Medium 3.1	95	92	90	90	90	79	79	77	72	68	83.2%
DeepSeek V3 (2025-03-24)	97	97	92	92	84	74	74	74	72	72	83.1%
ByteDance Seed 1.6 Flash	100	100	100	100	95	94	83	77	76	3	82.8%
Grok 4	100	97	87	87	84	81	77	77	74	56	82.3%
Gemini 2.5 Flash (Reasoning)	97	89	87	86	85	84	78	75	71	65	81.7%
Stealth: Healer Alpha	100	100	100	100	100	95	79	71	39	30	81.4%
Mistral Small 4 (Reasoning)	100	100	97	90	87	80	75	65	58	50	80.2%
DeepSeek V3 (2024-12-26)	92	90	89	87	87	82	77	70	65	59	79.9%
Claude Haiku 4.5	89	89	86	86	82	77	74	74	71	67	79.5%
Claude Sonnet 4.6	100	97	74	74	74	74	74	74	74	74	78.9%
Mistral Small Creative	90	90	90	87	80	79	75	70	65	63	78.9%
Mistral Large 3	90	90	90	84	84	84	82	66	59	59	78.8%
Grok 4 Fast	97	93	92	90	87	84	72	68	48	39	76.8%
GPT-4.1 Nano	84	84	83	83	82	77	75	72	66	55	76.1%
Ministral 3 14B	92	88	85	80	76	75	72	71	69	52	75.9%
Gemma 3 4B	88	88	87	80	77	75	72	65	63	52	74.8%
Grok 4.20 (Beta)	96	94	79	79	74	70	67	67	62	62	74.8%
Writer: Palmyra X5	89	87	87	78	76	75	73	73	54	48	73.9%
Qwen3 235B A22B Instruct 2507	95	92	90	87	85	79	73	62	43	23	73.0%
Claude 3 Haiku	97	84	83	82	78	75	74	63	61	31	72.9%
Ministral 3 8B	90	87	85	84	80	72	72	63	50	42	72.6%
Qwen 3.5 Plus (2026-02-15)	100	84	84	74	72	72	70	65	52	35	70.9%
Mistral Small 4	95	80	80	78	76	75	61	59	48	45	69.8%
Gemini 2.5 Flash Lite (Reasoning)	95	87	87	84	83	75	68	43	40	30	69.2%
DeepSeek V3.1	84	84	83	82	79	75	67	39	37	31	66.2%
Z.AI GLM 4.6	100	93	87	80	74	70	55	42	35	18	65.2%
Mistral Small 3.2 24B	80	79	77	70	64	59	57	52	51	48	63.8%
LFM2 24B	76	75	75	68	67	58	57	57	53	46	63.3%
Cohere Command R+ (Aug. 2024)	95	84	81	70	70	59	56	56	18	10	60.0%
WizardLM 2 8x22b	77	74	66	66	59	57	54	52	46	20	57.1%
Gemini 2.5 Flash Lite	85	74	73	61	61	60	50	39	37	22	56.2%
Ministral 3 3B	82	78	65	64	58	56	54	53	15	7	52.9%
Arcee AI: Trinity Large (Preview)	71	67	65	59	58	50	45	41	39	32	52.5%
Gemini 2.5 Flash	69	62	62	54	52	50	45	41	27	14	47.6%
Qwen 3 32B	73	66	63	46	45	37	34	27	24	16	43.1%
Mistral Large 2	81	73	57	46	43	28	19	19	17	14	39.6%
Hermes 3 70B	81	57	42	41	40	36	30	8	7	6	34.6%
Mistral Large	65	51	51	42	38	26	21	21	16	3	33.4%
Z.AI GLM 4.5	56	54	48	39	39	39	25	11	8	5	32.5%
Arcee AI: Trinity Mini	64	52	51	38	34	31	24	15	7	7	32.3%
Mistral NeMO	57	48	45	24	24	15	14	11	10	9	25.7%
Ministral 3B	39	32	31	30	27	26	26	21	7	6	24.5%
Rocinante 12B	56	43	35	31	26	21	14	3	1	0	23.1%
Ministral 8B	49	36	34	28	28	16	15	10	0	0	21.6%
DeepSeek-V2 Chat	25	23	18	18	15	13	10	8	7	4	14.2%

▼

Write sentences with 20 words each

Model	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Avg ▼
Claude Opus 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Pro (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
Z.AI GLM 5 Turbo	100	100	100	100	100	100	100	100	100	100	100.0%
Claude Sonnet 4.6 (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.1	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 397B A17B	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 122B	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
MoonshotAI: Kimi K2.5	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 27B	100	100	100	100	100	100	100	100	100	100	100.0%
ByteDance Seed 1.6	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3 Flash (Preview, Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini High	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.2	100	100	100	100	100	100	100	100	100	100	100.0%
MiniMax M2.7	100	100	100	100	100	100	100	100	100	100	100.0%
o4 Mini	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 35B	100	100	100	100	100	100	100	100	100	100	100.0%
ByteDance Seed 2.0 Mini	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 Flash	100	100	100	100	100	100	100	100	100	100	100.0%
Qwen 3.5 9B	100	100	100	100	100	100	100	100	100	100	100.0%
Gemini 3.1 Flash Lite (Preview)	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Mini (Reasoning, Low)	100	100	100	100	100	100	100	100	100	100	100.0%
Nemotron 3 Super	100	100	100	100	100	100	100	100	100	100	100.0%
Inception Mercury 2	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5 Nano	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 Nano (Reasoning)	100	100	100	100	100	100	100	100	100	100	100.0%
Nemotron 3 Nano	100	100	100	100	100	100	100	100	100	100	100.0%
GPT-5.4 (Reasoning)	100	100	100	100	100	100	100	100	100	94	99.4%
ByteDance Seed 2.0 Lite	100	100	100	100	100	100	100	100	100	93	99.3%
GPT-5.4 Nano (Reasoning, Low)	100	100	100	100	100	100	100	100	100	86	98.6%
GPT-5 Mini	100	100	100	100	100	100	100	100	100	83	98.3%
Z.AI GLM 5	100	100	100	100	100	100	100	100	100	80	98.0%
Grok 4.20 (Beta, Reasoning)	100	100	100	100	100	100	100	100	100	78	97.8%
MiniMax M2.5	100	100	100	100	100	100	100	100	100	75	97.5%
Stealth: Aurora Alpha	100	100	100	100	100	100	100	100	100	75	97.5%
Gemini 3 Flash (Preview)	100	100	100	100	100	100	95	95	94	90	97.5%
Gemini 3 Pro (Preview)	100	100	100	100	100	100	100	100	93	80	97.4%
Inception Mercury	100	100	100	100	100	100	100	84	84	84	95.2%
Z.AI GLM 4.7	100	100	100	100	100	100	100	100	100	51	95.1%
Mistral Small 4 (Reasoning)	100	100	100	100	94	93	90	90	89	84	94.1%
Aion 2.0	100	100	100	100	100	100	100	93	92	54	93.9%
ByteDance Seed 1.6 Flash	100	100	100	100	100	100	87	83	78	75	92.3%
Z.AI GLM 4.7 Flash	100	100	100	100	100	93	90	74	74	60	89.2%
Claude Opus 4.5	100	96	88	88	84	80	75	75	74	60	82.1%
GPT-5.4 Mini	100	92	87	83	78	76	74	74	70	59	79.3%
GPT-4.1	93	92	85	84	84	80	72	72	67	57	78.7%
Stealth: Healer Alpha	100	100	100	100	100	100	92	37	34	20	78.3%
GPT-4o, May 13th (temp=0)	100	100	88	85	80	80	73	64	43	18	73.2%
GPT-4o Mini (temp=0)	72	72	72	72	72	72	72	72	72	68	71.3%
GPT-5.4	100	90	80	70	67	66	59	59	51	40	68.4%
Grok 4	84	78	76	69	68	68	67	61	54	39	66.3%
Claude Opus 4	83	75	70	66	66	61	61	61	56	53	65.1%
GPT-4o Mini (temp=1)	100	80	76	72	70	65	59	55	34	23	63.2%
Gemini 2.5 Pro	83	80	80	80	78	59	57	51	38	20	62.7%
Mistral Medium 3.1	76	72	68	68	67	61	58	57	54	29	60.9%
GPT-4.1 Nano	76	76	76	65	64	59	59	57	38	30	60.1%
Qwen 2.5 72B	100	61	61	61	61	61	61	61	40	35	60.0%
Claude Opus 4.6	100	93	80	61	55	47	47	37	37	32	58.9%
GPT-4o, May 13th (temp=1)	92	87	75	67	64	54	48	39	30	11	56.7%
Llama 3.1 70B	74	69	60	58	54	53	50	46	43	38	54.5%
Claude Sonnet 4.5	92	72	69	65	59	58	49	42	20	2	52.9%
Claude Sonnet 4	91	78	76	72	66	49	32	17	12	3	49.7%
GPT-4.1 Mini	87	82	59	59	51	42	38	34	32	4	48.8%
Claude 3.5 Haiku	84	84	83	56	49	47	39	24	16	3	48.6%
Llama 3.1 Nemotron 70B	66	60	53	52	45	39	39	37	29	29	44.9%
Llama 3.1 8B	84	74	74	48	45	33	27	24	21	5	43.6%
Gemini 2.5 Flash Lite (Reasoning)	67	65	55	53	52	49	35	25	13	10	42.4%
Claude 3.7 Sonnet	59	53	52	47	47	45	45	27	24	2	40.1%
Ministral 3 14B	65	51	49	46	44	42	32	32	4	3	36.8%
Qwen3 235B A22B Instruct 2507	75	58	57	39	39	31	24	13	12	0	34.8%
Writer: Palmyra X5	71	58	51	44	38	37	22	14	8	0	34.2%
Grok 4.1 Fast	100	95	85	21	19	15	2	0	0	0	33.8%
GPT-4o, Aug. 6th (temp=1)	59	57	52	46	34	27	22	14	12	9	33.2%
Qwen 3 32B	56	55	48	47	38	28	24	20	7	3	32.5%
Claude Sonnet 4.6	87	77	34	32	23	23	22	15	1	0	31.4%
DeepSeek V3 (2025-03-24)	74	58	51	39	27	24	18	11	8	0	31.1%
Gemma 3 27B	60	56	53	47	44	28	17	2	2	2	30.9%
Stealth: Hunter Alpha	83	72	66	56	25	0	0	0	0	0	30.3%
Claude Haiku 4.5	67	66	57	50	36	10	0	0	0	0	28.7%
Claude 3.5 Sonnet	51	47	45	40	19	16	13	13	6	1	25.1%
DeepSeek V3 (2024-12-26)	49	44	35	21	21	19	18	10	2	0	22.0%
Mistral Small Creative	44	40	28	27	22	18	16	13	3	0	21.1%
Mistral Small 3.2 24B	51	47	27	19	7	5	1	0	0	0	15.7%
GPT-4o, Aug. 6th (temp=0)	25	19	17	15	13	13	12	12	12	11	14.9%
Mistral Small 4	49	25	19	16	13	9	6	0	0	0	13.7%
Gemini 2.5 Flash (Reasoning)	51	34	12	10	9	6	3	1	0	0	12.8%
Z.AI GLM 4.6	59	36	7	6	5	3	2	0	0	0	11.9%
Grok 4.20 (Beta)	66	15	11	5	3	3	2	0	0	0	10.4%
Gemini 2.5 Flash Lite	47	34	4	2	2	0	0	0	0	0	8.9%
WizardLM 2 8x22b	41	21	14	5	5	1	1	0	0	0	8.9%
Grok 4 Fast	33	23	15	8	7	1	0	0	0	0	8.6%
Hermes 3 70B	27	16	15	8	7	6	0	0	0	0	7.9%
GPT-5.4 Nano	47	11	4	4	4	3	3	1	0	0	7.7%
Ministral 3B	23	19	15	11	4	0	0	0	0	0	7.3%
Claude 3 Haiku	27	15	13	10	4	0	0	0	0	0	6.9%
Ministral 3 3B	23	19	10	4	2	2	0	0	0	0	5.9%
Gemma 3 12B	13	13	9	9	2	2	2	0	0	0	5.1%
Cohere Command R+ (Aug. 2024)	25	19	0	0	0	0	0	0	0	0	4.5%
Qwen 3.5 Plus (2026-02-15)	23	12	3	3	2	0	0	0	0	0	4.4%
Hermes 3 405B	20	16	0	0	0	0	0	0	0	0	3.6%
Gemma 3 4B	12	10	2	1	0	0	0	0	0	0	2.5%
Ministral 8B	13	7	2	2	1	0	0	0	0	0	2.5%
Arcee AI: Trinity Mini	8	8	7	0	0	0	0	0	0	0	2.2%
DeepSeek V3.1	7	6	0	0	0	0	0	0	0	0	1.3%
Ministral 3 8B	9	1	0	0	0	0	0	0	0	0	1.0%
LFM2 24B	6	2	0	0	0	0	0	0	0	0	0.9%
Mistral Large	6	0	0	0	0	0	0	0	0	0	0.6%
Mistral Large 3	2	1	1	1	0	0	0	0	0	0	0.5%
Mistral NeMO	2	0	0	0	0	0	0	0	0	0	0.2%
DeepSeek V3.2	1	0	0	0	0	0	0	0	0	0	0.1%
Gemini 2.5 Flash	0	0	0	0	0	0	0	0	0	0	0.0%
Arcee AI: Trinity Large (Preview)	0	0	0	0	0	0	0	0	0	0	0.0%
Rocinante 12B	0	0	0	0	0	0	0	0	0	0	0.0%
DeepSeek-V2 Chat	0	0	0	0	0	0	0	0	0	0	0.0%
Z.AI GLM 4.5	0	0	0	0	0	0	0	0	0	0	0.0%
Mistral Large 2	0	0	0	0	0	0	0	0	0	0	0.0%

Matches word count

Overall Performance

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)

Individual Scenarios

Write sentences with 5 words each

Write sentences with 10 words each

Write sentences with 20 words each