Character dialogue (Hindi) in a story

Language Writing

Can the model generate text in different languages?

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
Qwen3.6 Max Preview	100%
Z.AI GLM 5 Turbo	100%
Grok 4.3 (Reasoning)	100%
GPT-5.5 (Reasoning)	100%
Claude Sonnet 4.6	100%
o4 Mini High	100%
Claude Opus 4.7	100%
o4 Mini	100%
Gemma 4 31B	100%
GPT-OSS 120B	100%
Z.AI GLM 4.5	100%
GPT-5.4 Mini (Reasoning, Low)	100%
Gemini 3 Flash (Preview)	100%
DeepSeek-V2 Chat	100%
Inception Mercury 2	100%
Stealth: Aurora Alpha	100%
GPT-4.1 Mini	100%
GPT-5 Nano	100%
GPT-4o, Aug. 6th (temp=0)	100%
GPT-5.4 Mini	100%

	Score	Cost	Time
Stealth: Aurora Alpha	100%	—	3.2s
Inception Mercury	91%	$0.0002	1.5s
GPT-4.1 Nano	90%	$0.0001	4.0s
Mistral NeMO	80%	$0.0001	3.7s
Inception Mercury 2	100%	$0.0006	1.3s
GPT-4.1 Mini	100%	$0.0005	5.0s
GPT-4o Mini (temp=0)	100%	$0.0003	7.3s
GPT-4o Mini (temp=1)	100%	$0.0003	5.9s
Claude 3 Haiku	100%	$0.0007	4.1s
Gemini 3.1 Flash Lite	84%	$0.0010	3.7s
Nemotron 3 Nano	100%	$0.0002	8.8s
Gemini 3.1 Flash Lite (Reasoning)	92%	$0.0010	6.9s
Nemotron 3 Super	96%	$0.0000	31.4s
GPT-5.4 Mini (Reasoning, Low)	100%	$0.0021	3.2s
Gemma 4 31B	100%	$0.0002	15.8s
GPT-5.4 Mini	100%	$0.0024	2.8s
GPT-5.4 Nano (Reasoning)	91%	$0.0015	5.7s
GPT-OSS 120B	100%	$0.0003	21.3s
Gemini 3 Flash (Preview)	100%	$0.0021	5.8s
DeepSeek V3.1	100%	$0.0011	16.3s

	Score	Cost	Speed	Stability
Inception Mercury 2	100%	$0.0006	1.3s	100%
Stealth: Aurora Alpha	100%	—	3.2s	100%
GPT-4.1 Mini	100%	$0.0005	5.0s	100%
Claude 3 Haiku	100%	$0.0007	4.1s	100%
GPT-4o Mini (temp=1)	100%	$0.0003	5.9s	100%
GPT-4o Mini (temp=0)	100%	$0.0003	7.3s	100%
Nemotron 3 Nano	100%	$0.0002	8.8s	100%
GPT-5.4 Mini (Reasoning, Low)	100%	$0.0021	3.2s	100%
GPT-5.4 Mini	100%	$0.0024	2.8s	100%
Gemini 3 Flash (Preview)	100%	$0.0021	5.8s	100%
Gemma 4 31B	100%	$0.0002	15.8s	100%
DeepSeek V3.1	100%	$0.0011	16.3s	100%
GPT-OSS 120B	100%	$0.0003	21.3s	100%
Z.AI GLM 4.5	100%	$0.0018	16.6s	100%
GPT-4o, Aug. 6th (temp=0)	100%	$0.0055	6.4s	100%
Z.AI GLM 5 Turbo	100%	$0.0041	11.7s	100%
DeepSeek-V2 Chat	100%	$0.0002	26.9s	100%
Hermes 3 405B	98%	$0.0000	18.9s	90%
o4 Mini	100%	$0.0079	19.4s	100%
GPT-4o, Aug. 6th (temp=1)	97%	$0.0049	5.6s	89%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
118	Qwen3.6 Max Preview	$0.040	2.8m	100%	100	100	100	100	100	100%
16	Z.AI GLM 5 Turbo	$0.0041	11.7s	100%	100	100	100	100	100	100%
38	Grok 4.3 (Reasoning)	$0.013	1.2m	100%	100	100	100	100	100	100%
49	GPT-5.5 (Reasoning)	$0.035	28.2s	100%	100	100	100	100	100	100%
22	Claude Sonnet 4.6	$0.013	16.2s	100%	100	100	100	100	100	100%
24	o4 Mini High	$0.015	31.2s	100%	100	100	100	100	100	100%
58	Claude Opus 4.7	$0.042	20.7s	100%	100	100	100	100	100	100%
19	o4 Mini	$0.0079	19.4s	100%	100	100	100	100	100	100%
11	Gemma 4 31B	$0.0002	15.8s	100%	100	100	100	100	100	100%
13	GPT-OSS 120B	$0.0003	21.3s	100%	100	100	100	100	100	100%
14	Z.AI GLM 4.5	$0.0018	16.6s	100%	100	100	100	100	100	100%
8	GPT-5.4 Mini (Reasoning, Low)	$0.0021	3.2s	100%	100	100	100	100	100	100%
10	Gemini 3 Flash (Preview)	$0.0021	5.8s	100%	100	100	100	100	100	100%
17	DeepSeek-V2 Chat	$0.0002	26.9s	100%	100	100	100	100	100	100%
1	Inception Mercury 2	$0.0006	1.3s	100%	100	100	100	100	100	100%
2	Stealth: Aurora Alpha	—	3.2s	100%	100	100	100	100	100	100%
3	GPT-4.1 Mini	$0.0005	5.0s	100%	100	100	100	100	100	100%
25	GPT-5 Nano	$0.0027	1.3m	100%	100	100	100	100	100	100%
15	GPT-4o, Aug. 6th (temp=0)	$0.0055	6.4s	100%	100	100	100	100	100	100%
9	GPT-5.4 Mini	$0.0024	2.8s	100%	100	100	100	100	100	100%
12	DeepSeek V3.1	$0.0011	16.3s	100%	100	100	100	100	100	100%
5	GPT-4o Mini (temp=1)	$0.0003	5.9s	100%	100	100	100	100	100	100%
6	GPT-4o Mini (temp=0)	$0.0003	7.3s	100%	100	100	100	100	100	100%
7	Nemotron 3 Nano	$0.0002	8.8s	100%	100	100	100	100	100	100%
4	Claude 3 Haiku	$0.0007	4.1s	100%	100	100	100	100	100	100%
41	GPT-5.5 (Reasoning, Low)	$0.031	25.8s	99%	100	100	100	100	99	100%
45	GPT-5.5	$0.032	27.8s	98%	100	100	100	100	98	100%
34	Claude Opus 4.5	$0.023	17.5s	96%	100	100	100	100	95	99%
21	GPT-4o, May 13th (temp=0)	$0.0091	7.3s	94%	100	100	100	100	92	98%
18	Hermes 3 405B	$0.0000	18.9s	90%	100	100	100	100	88	98%
27	Z.AI GLM 5.1	$0.0065	39.3s	89%	100	100	100	100	86	97%
20	GPT-4o, Aug. 6th (temp=1)	$0.0049	5.6s	89%	100	100	100	100	86	97%
23	Nemotron 3 Super	$0.0000	31.4s	89%	100	100	100	90	88	96%
33	Gemini 2.5 Flash (Reasoning)	$0.0072	13.9s	73%	100	100	100	100	67	93%
56	Z.AI GLM 4.6	$0.0046	1.4m	74%	100	100	100	95	67	92%
40	GPT-5.4	$0.012	18.2s	69%	100	100	100	100	61	92%
26	Gemini 3.1 Flash Lite (Reasoning)	$0.0010	6.9s	68%	100	100	100	100	60	92%
29	Grok 4.20 (Beta)	$0.0038	3.3s	68%	100	100	100	100	60	92%
48	GPT-5.2	$0.013	19.9s	65%	100	100	100	100	56	91%
30	GPT-5.4 Nano (Reasoning)	$0.0015	5.7s	65%	100	100	100	100	56	91%
63	Grok 4.20 (Reasoning)	$0.010	55.8s	64%	100	100	100	100	56	91%
47	GPT-5 Mini	$0.0071	37.3s	64%	100	100	100	100	55	91%
28	Inception Mercury	$0.0002	1.5s	64%	100	100	100	100	55	91%
66	Grok 4.20 (Beta, Reasoning)	$0.025	19.3s	63%	100	100	100	100	54	91%
113	Claude Opus 4.7 (Reasoning)	$0.048	23.2s	62%	100	100	100	100	53	91%
130	GPT-5	$0.046	1.4m	62%	100	100	100	100	53	91%
94	GPT-5.1	$0.027	56.7s	61%	100	100	100	100	51	90%
31	Gemini 2.5 Flash	$0.0029	6.3s	68%	100	100	100	92	58	90%
32	GPT-4.1 Nano	$0.0001	4.0s	60%	100	100	100	100	50	90%
61	Qwen 3.6 35B	$0.0075	44.5s	57%	100	100	100	100	46	89%
37	MiniMax M2.5	$0.0013	21.2s	63%	100	100	100	93	53	89%
39	GPT-4.1	$0.0037	6.2s	56%	100	100	100	100	45	89%
54	Claude 3.7 Sonnet	$0.014	16.8s	61%	100	100	100	95	50	89%
50	Claude 3.5 Sonnet	$0.011	17.8s	61%	100	100	100	94	50	89%
36	Hermes 3 70B	$0.0003	21.5s	66%	100	100	100	71	60	86%
35	Gemini 3.1 Flash Lite	$0.0010	3.7s	61%	100	100	100	60	60	84%
51	Z.AI GLM 4.5 Air	$0.0018	37.4s	59%	100	100	100	67	52	84%
59	GPT-5.4 (Reasoning, Low)	$0.012	16.1s	59%	100	100	100	59	57	83%
43	GPT-5.4 Mini (Reasoning)	$0.0052	8.2s	58%	100	100	100	60	55	83%
44	Claude Haiku 4.5	$0.0043	8.9s	57%	100	100	100	60	53	83%
75	Grok 4	$0.014	29.4s	54%	100	100	100	56	50	81%
52	Stealth: Hunter Alpha	$0.0000	28.0s	53%	100	100	93	67	45	81%
42	GPT-5.4 Nano	$0.0016	6.1s	53%	100	100	98	55	50	81%
120	Gemini 2.5 Pro	$0.026	22.5s	20%	100	100	100	100	0	80%
87	Xiaomi MIMO v2.5 Pro	$0.0041	23.3s	20%	100	100	100	100	0	80%
46	DeepSeek V4 Flash	$0.0002	13.6s	51%	100	100	100	50	50	80%
69	Mistral NeMO	$0.0001	3.7s	20%	100	100	100	100	0	80%
126	Claude Sonnet 4.6 (Reasoning)	$0.042	47.1s	50%	100	100	100	50	47	79%
53	Mistral Small 4 (Reasoning)	$0.0011	16.9s	49%	100	100	91	50	50	78%
60	Claude Sonnet 4	$0.011	11.6s	58%	93	92	92	57	53	78%
90	GPT-4o, May 13th (temp=1)	$0.0092	7.6s	22%	100	100	100	88	0	78%
74	Gemma 4 26B (Reasoning)	$0.0009	43.4s	41%	100	100	67	60	58	77%
100	GPT-5.4 (Reasoning)	$0.018	26.7s	39%	100	100	65	58	57	76%
70	Gemini 3 Flash (Preview, Reasoning)	$0.0053	11.9s	37%	100	100	63	58	57	76%
55	Stealth: Healer Alpha	$0.0000	12.6s	47%	100	90	72	57	57	75%
62	Gemini 3.1 Flash Lite (Preview)	$0.0010	3.4s	38%	100	100	67	57	50	75%
67	Gemma 4 26B	$0.0004	41.2s	47%	100	88	70	60	56	75%
64	Grok 4.3	$0.0010	3.7s	36%	100	100	63	57	53	75%
84	Aion 2.0	$0.0027	39.0s	36%	100	100	63	60	50	75%
133	Gemini 3.1 Pro (Preview)	$0.039	46.0s	37%	100	100	67	53	50	74%
122	Qwen 3.5 Plus (2026-04-20)	$0.013	1.4m	30%	100	100	57	50	50	71%
92	Z.AI GLM 4.7 Flash	$0.0014	46.3s	30%	100	100	57	50	50	71%
76	GPT-5.4 Nano (Reasoning, Low)	$0.0022	8.1s	30%	100	99	55	53	49	71%
115	MoonshotAI: Kimi K2.5	$0.0087	1.1m	28%	100	100	54	54	47	71%
57	Gemini 2.5 Flash Lite	$0.0006	5.3s	47%	93	78	64	60	60	71%
99	Qwen 3.6 Flash	$0.0080	30.9s	29%	100	100	55	50	50	71%
127	ByteDance Seed 2.0 Mini	$0.0025	2.7m	46%	100	67	67	60	57	70%
86	Qwen 3.5 Plus (2026-02-15)	$0.0017	22.0s	27%	100	100	54	50	46	70%
117	ByteDance Seed 2.0 Lite	$0.0068	1.3m	29%	100	100	57	50	43	70%
82	DeepSeek V4 Flash (Reasoning)	$0.0003	13.6s	25%	100	100	50	50	45	69%
98	Cohere Command R+ (Aug. 2024)	$0.0060	13.4s	21%	100	100	88	55	0	68%
147	MoonshotAI: Kimi K2.6	$0.021	3.3m	23%	100	100	50	45	43	68%
88	Gemma 3 27B	$0.0003	28.3s	28%	100	87	50	50	50	67%
73	Llama 3.1 70B	$0.0006	12.9s	37%	100	60	57	56	54	65%
91	Gemma 3 12B	$0.0003	32.2s	30%	100	81	55	53	38	65%
68	Grok 4.20	$0.0021	11.0s	43%	93	67	62	55	50	65%
106	Qwen 3.5 35B	$0.010	38.5s	37%	100	62	58	53	52	65%
89	Gemini 2.5 Flash Lite (Reasoning)	$0.0021	29.6s	35%	100	67	56	50	50	64%
132	Claude Opus 4.6	$0.036	33.1s	35%	100	59	55	54	52	64%
79	Xiaomi MIMO v2.5	$0.0027	17.0s	39%	95	63	59	50	50	63%
96	Gemma 4 31B (Reasoning)	$0.0006	1.6m	60%	67	64	64	64	58	63%
144	Claude Opus 4.6 (Reasoning)	$0.046	43.0s	32%	100	55	52	52	52	62%
114	Arcee AI: Trinity Mini	$0.0002	45.8s	14%	100	100	55	50	0	61%
83	Qwen 3 32B	$0.0008	34.6s	44%	78	63	55	54	54	61%
65	Llama 3.1 8B	$0.0001	3.6s	46%	71	70	56	54	50	60%
108	DeepSeek V4 Pro (Reasoning)	$0.0017	52.3s	30%	100	54	50	50	47	60%
93	Qwen 2.5 72B	$0.0004	20.5s	28%	100	53	48	46	46	59%
124	Z.AI GLM 5	$0.0071	1.4m	29%	100	50	50	47	44	58%
103	WizardLM 2 8x22b	$0.0009	20.9s	22%	100	64	63	57	0	57%
125	Qwen 3.5 9B	$0.0010	1.4m	19%	100	76	58	50	0	57%
95	ByteDance Seed 1.6	$0.0040	50.1s	50%	63	60	55	55	50	56%
111	Arcee AI: Trinity Large (Preview)	$0.0000	11.0s	6%	100	100	80	0	0	56%
102	Qwen 3.5 122B	$0.012	40.3s	55%	57	56	56	55	55	56%
109	Qwen 3.5 27B	$0.0097	48.7s	44%	70	56	53	50	47	55%
85	MiniMax M2.7	$0.0015	28.3s	47%	68	55	55	50	47	55%
110	Z.AI GLM 4.7	$0.0055	1.3m	52%	58	55	54	54	53	55%
146	Claude Opus 4	$0.055	28.5s	38%	78	55	50	47	42	54%
80	Mistral Large 3	$0.0013	16.1s	46%	60	57	50	50	50	53%
140	DeepSeek V3.2	$0.0005	1.6m	6%	100	100	67	0	0	53%
71	Ministral 3B	$0.0000	2.7s	46%	60	53	50	50	50	53%
101	Claude Sonnet 4.5	$0.012	14.1s	45%	62	53	50	50	47	52%
81	Grok 4.1 Fast	$0.0008	17.4s	46%	56	56	50	50	45	51%
119	DeepSeek V3 (2025-03-24)	$0.0006	24.8s	6%	100	100	56	0	0	51%
142	Qwen 3.6 27B	$0.019	1.8m	46%	57	52	50	48	47	51%
77	Grok 4 Fast	$0.0005	8.4s	45%	57	56	50	45	44	51%
136	Qwen 3.5 397B A17B	$0.015	1.9m	48%	53	50	50	50	47	50%
78	Mistral Large	$0.0032	9.4s	50%	50	50	50	50	50	50%
72	Mistral Small Creative	$0.0003	5.9s	50%	50	50	50	50	50	50%
97	Qwen 3.5 Flash	$0.0018	40.7s	47%	53	52	50	47	44	49%
138	Gemini 3 Pro (Preview)	$0.029	22.8s	30%	60	56	54	54	0	45%
105	ByteDance Seed 1.6 Flash	$0.0006	15.5s	30%	58	56	54	53	0	44%
104	Mistral Small 3.2 24B	$0.0003	10.4s	28%	59	55	50	50	0	43%
123	Mistral Large 2	$0.0046	23.2s	13%	100	56	55	0	0	42%
107	Gemma 3 4B	$0.0001	14.0s	29%	58	50	50	45	0	41%
128	DeepSeek V3 (2024-12-26)	$0.0008	21.0s	0%	100	100	0	0	0	40%
129	Qwen3 235B A22B Instruct 2507	$0.0006	23.8s	0%	100	100	0	0	0	40%
121	Ministral 3 8B	$0.0002	6.4s	0%	100	100	0	0	0	40%
112	Mistral Small 4	$0.0003	5.6s	24%	60	57	56	0	0	35%
116	Ministral 8B	$0.0001	16.4s	22%	64	56	50	0	0	34%
137	DeepSeek V4 Pro	$0.0025	32.5s	0%	100	60	0	0	0	32%
135	LFM2 24B	$0.0001	20.1s	0%	70	57	0	0	0	25%
131	Ministral 3 3B	$0.0001	2.5s	0%	67	56	0	0	0	24%
141	Mistral Medium 3.1	$0.0022	22.8s	0%	67	50	0	0	0	23%
134	Rocinante 12B	$0.0002	14.7s	0%	67	50	0	0	0	23%
139	Llama 3.1 Nemotron 70B	$0.0004	22.6s	0%	60	50	0	0	0	22%
145	Writer: Palmyra X5	$0.0060	14.9s	0%	0	0	0	0	0	0%
143	Ministral 3 14B	$0.0003	9.9s	0%	0	0	0	0	0	0%
73.19%

Language Writing

Character dialogue (Hindi) in a story

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)