What's the color of the car?

Data extraction

Extract key details from a given block of text.

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
Claude Opus 4.6 (Reasoning)	100%
Gemini 3.1 Pro (Preview)	100%
Z.AI GLM 5 Turbo	100%
Claude Sonnet 4.6 (Reasoning)	100%
GPT-5.4 (Reasoning)	100%
GPT-5 Mini	100%
GPT-5.1	100%
Claude Opus 4.6	100%
GPT-5	100%
Qwen 3.5 397B A17B	100%
Qwen 3.5 122B	100%
GPT-5.4 (Reasoning, Low)	100%
Z.AI GLM 5	100%
Claude Sonnet 4.6	100%
MoonshotAI: Kimi K2.5	100%
Qwen 3.5 27B	100%
ByteDance Seed 1.6	100%
GPT-5.4 Mini (Reasoning)	100%
Gemini 3 Flash (Preview, Reasoning)	100%
o4 Mini High	100%

	Score	Cost	Time
Gemma 3 4B	100%	$0.0000	221ms
Ministral 3B	100%	$0.0000	273ms
Ministral 8B	100%	$0.0000	256ms
LFM2 24B	100%	$0.0000	733ms
Mistral NeMO	100%	$0.0000	536ms
Ministral 3 3B	100%	$0.0000	293ms
Mistral Small Creative	100%	$0.0000	412ms
Qwen3 235B A22B Instruct 2507	100%	$0.0000	758ms
Ministral 3 8B	100%	$0.0000	361ms
Mistral Small 3.2 24B	100%	$0.0000	406ms
Gemini 2.5 Flash Lite	100%	$0.0000	375ms
Llama 3.1 8B	100%	$0.0000	308ms
Ministral 3 14B	100%	$0.0000	362ms
Gemma 3 12B	100%	$0.0000	403ms
Arcee AI: Trinity Large (Preview)	100%	$0.0000	554ms
Gemma 3 27B	100%	$0.0000	518ms
Mistral Small 4	100%	$0.0000	488ms
Inception Mercury	100%	$0.0000	508ms
Stealth: Aurora Alpha	100%	—	533ms
Mistral Medium 3.1	100%	$0.0000	441ms

	Score	Cost	Speed	Stability
Gemma 3 4B	100%	$0.0000	221ms	100%
Ministral 3B	100%	$0.0000	273ms	100%
Ministral 8B	100%	$0.0000	256ms	100%
Ministral 3 3B	100%	$0.0000	293ms	100%
Llama 3.1 8B	100%	$0.0000	308ms	100%
Gemini 2.5 Flash Lite	100%	$0.0000	375ms	100%
Ministral 3 8B	100%	$0.0000	361ms	100%
Gemma 3 12B	100%	$0.0000	403ms	100%
Ministral 3 14B	100%	$0.0000	362ms	100%
Mistral Small 3.2 24B	100%	$0.0000	406ms	100%
Mistral Small Creative	100%	$0.0000	412ms	100%
Arcee AI: Trinity Large (Preview)	100%	$0.0000	554ms	100%
Gemma 3 27B	100%	$0.0000	518ms	100%
Mistral Small 4	100%	$0.0000	488ms	100%
Inception Mercury	100%	$0.0000	508ms	100%
Mistral NeMO	100%	$0.0000	536ms	100%
Mistral Medium 3.1	100%	$0.0000	441ms	100%
Stealth: Aurora Alpha	100%	—	533ms	100%
Gemini 2.5 Flash	100%	$0.0000	549ms	100%
GPT-5.4 Nano	100%	$0.0000	578ms	100%

Median	Evaluator	Top 3	Flop 3
100.0%	Matches Regex	100Ministral 8B 100DeepSeek V3 (2025-03-24) 100GPT-4.1 Mini	80Gemini 2.5 Flash (Reasoning)
100.0%	Matches text	100ByteDance Seed 2.0 Lite 100Qwen 2.5 72B 100GPT-5 Nano	30Mistral Large 40WizardLM 2 8x22b 70Llama 3.1 Nemotron 70B

Data extraction

What's the color of the car?

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Total
95	Claude Opus 4.6 (Reasoning)	$0.0016	2.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
108	Gemini 3.1 Pro (Preview)	$0.0032	5.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
91	Z.AI GLM 5 Turbo	$0.0008	3.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
86	Claude Sonnet 4.6 (Reasoning)	$0.0009	1.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
80	GPT-5.4 (Reasoning)	$0.0006	2.4s	100%	100	100	100	100	100	100	100	100	100	100	100%
67	GPT-5 Mini	$0.0003	2.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
68	GPT-5.1	$0.0003	2.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
71	Claude Opus 4.6	$0.0004	2.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
92	GPT-5	$0.0013	2.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
103	Qwen 3.5 397B A17B	$0.0017	13.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
100	Qwen 3.5 122B	$0.0018	4.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
70	GPT-5.4 (Reasoning, Low)	$0.0005	1.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
110	Z.AI GLM 5	$0.0016	17.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
53	Claude Sonnet 4.6	$0.0003	1.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
94	MoonshotAI: Kimi K2.5	$0.0008	6.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
104	Qwen 3.5 27B	$0.0021	10.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
72	ByteDance Seed 1.6	$0.0002	3.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
63	GPT-5.4 Mini (Reasoning)	$0.0002	2.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
78	Gemini 3 Flash (Preview, Reasoning)	$0.0006	2.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
75	o4 Mini High	$0.0006	2.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
77	GPT-5.2	$0.0004	2.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
69	Claude Opus 4.5	$0.0004	1.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
64	Grok 4.1 Fast	$0.0001	3.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
93	Aion 2.0	$0.0006	8.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
114	Z.AI GLM 4.6	$0.0014	24.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
88	MiniMax M2.7	$0.0003	6.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
112	Gemini 3 Pro (Preview)	$0.0035	6.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
56	Claude Sonnet 4	$0.0003	1.4s	100%	100	100	100	100	100	100	100	100	100	100	100%
84	MiniMax M2.5	$0.0003	5.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
102	Z.AI GLM 4.7	$0.0009	15.2s	100%	100	100	100	100	100	100	100	100	100	100	100%
44	GPT-4.1	$0.0001	1.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
111	Gemini 2.5 Pro	$0.0036	4.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
79	o4 Mini	$0.0006	2.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
113	Grok 4	$0.0037	5.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
59	Claude Sonnet 4.5	$0.0003	1.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
99	Qwen 3.5 35B	$0.0015	5.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
97	Claude Opus 4	$0.0013	4.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
74	Stealth: Hunter Alpha	$0.0000	5.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
61	ByteDance Seed 2.0 Mini	$0.0000	3.2s	100%	100	100	100	100	100	100	100	100	100	100	100%
87	Qwen 3.5 Flash	$0.0003	5.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
40	Z.AI GLM 4.5	$0.0000	1.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
41	Grok 4 Fast	$0.0001	1.2s	100%	100	100	100	100	100	100	100	100	100	100	100%
106	Qwen 3.5 9B	$0.0002	24.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
38	Qwen 3.5 Plus (2026-02-15)	$0.0000	1.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
82	Stealth: Healer Alpha	$0.0000	6.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
22	Gemini 3.1 Flash Lite (Preview)	$0.0000	638ms	100%	100	100	100	100	100	100	100	100	100	100	100%
58	GPT-5.4 Mini (Reasoning, Low)	$0.0001	2.4s	100%	100	100	100	100	100	100	100	100	100	100	100%
52	Gemini 2.5 Flash Lite (Reasoning)	$0.0001	2.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
26	Mistral Large 3	$0.0000	617ms	100%	100	100	100	100	100	100	100	100	100	100	100%
90	GPT-4o, May 13th (temp=0)	$0.0003	6.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
27	Gemini 3 Flash (Preview)	$0.0000	693ms	100%	100	100	100	100	100	100	100	100	100	100	100%
39	Claude Haiku 4.5	$0.0001	1.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
36	DeepSeek-V2 Chat	$0.0000	1.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
101	Z.AI GLM 4.7 Flash	$0.0003	14.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
60	ByteDance Seed 2.0 Lite	$0.0001	2.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
54	Nemotron 3 Super	$0.0000	2.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
46	GPT-5.4	$0.0002	550ms	100%	100	100	100	100	100	100	100	100	100	100	100%
85	Claude 3.5 Sonnet	$0.0003	5.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
98	Grok 4.20 (Beta)	$0.0001	12.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
31	Inception Mercury 2	$0.0001	379ms	100%	100	100	100	100	100	100	100	100	100	100	100%
89	GPT-4o, May 13th (temp=1)	$0.0003	6.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
18	Stealth: Aurora Alpha	—	533ms	100%	100	100	100	100	100	100	100	100	100	100	100%
35	Claude 3.5 Haiku	$0.0001	861ms	100%	100	100	100	100	100	100	100	100	100	100	100%
29	DeepSeek V3 (2024-12-26)	$0.0000	891ms	100%	100	100	100	100	100	100	100	100	100	100	100%
65	Claude 3.7 Sonnet	$0.0003	2.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
37	GPT-4.1 Mini	$0.0000	1.2s	100%	100	100	100	100	100	100	100	100	100	100	100%
73	Hermes 3 405B	$0.0000	5.4s	100%	100	100	100	100	100	100	100	100	100	100	100%
43	GPT-4o, Aug. 6th (temp=1)	$0.0002	848ms	100%	100	100	100	100	100	100	100	100	100	100	100%
66	GPT-5 Nano	$0.0001	3.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
42	GPT-4o, Aug. 6th (temp=0)	$0.0002	824ms	100%	100	100	100	100	100	100	100	100	100	100	100%
28	GPT-5.4 Mini	$0.0001	553ms	100%	100	100	100	100	100	100	100	100	100	100	100%
33	Mistral Large 2	$0.0001	309ms	100%	100	100	100	100	100	100	100	100	100	100	100%
62	Mistral Small 4 (Reasoning)	$0.0002	2.4s	100%	100	100	100	100	100	100	100	100	100	100	100%
49	DeepSeek V3.1	$0.0000	2.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
47	DeepSeek V3.2	$0.0000	2.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
81	Qwen 3 32B	$0.0001	5.6s	100%	100	100	100	100	100	100	100	100	100	100	100%
34	DeepSeek V3 (2025-03-24)	$0.0000	1.2s	100%	100	100	100	100	100	100	100	100	100	100	100%
50	GPT-5.4 Nano (Reasoning)	$0.0001	1.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
6	Gemini 2.5 Flash Lite	$0.0000	375ms	100%	100	100	100	100	100	100	100	100	100	100	100%
19	Gemini 2.5 Flash	$0.0000	549ms	100%	100	100	100	100	100	100	100	100	100	100	100%
23	Qwen3 235B A22B Instruct 2507	$0.0000	758ms	100%	100	100	100	100	100	100	100	100	100	100	100%
55	Writer: Palmyra X5	$0.0002	1.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
15	Inception Mercury	$0.0000	508ms	100%	100	100	100	100	100	100	100	100	100	100	100%
45	GPT-5.4 Nano (Reasoning, Low)	$0.0000	1.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
96	GPT-4o Mini (temp=1)	$0.0000	12.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
10	Mistral Small 3.2 24B	$0.0000	406ms	100%	100	100	100	100	100	100	100	100	100	100	100%
8	Gemma 3 12B	$0.0000	403ms	100%	100	100	100	100	100	100	100	100	100	100	100%
24	Llama 3.1 70B	$0.0001	413ms	100%	100	100	100	100	100	100	100	100	100	100	100%
57	GPT-4o Mini (temp=0)	$0.0000	3.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
13	Gemma 3 27B	$0.0000	518ms	100%	100	100	100	100	100	100	100	100	100	100	100%
17	Mistral Medium 3.1	$0.0000	441ms	100%	100	100	100	100	100	100	100	100	100	100	100%
83	Nemotron 3 Nano	$0.0000	6.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
14	Mistral Small 4	$0.0000	488ms	100%	100	100	100	100	100	100	100	100	100	100	100%
25	Qwen 2.5 72B	$0.0000	625ms	100%	100	100	100	100	100	100	100	100	100	100	100%
20	GPT-5.4 Nano	$0.0000	578ms	100%	100	100	100	100	100	100	100	100	100	100	100%
12	Arcee AI: Trinity Large (Preview)	$0.0000	554ms	100%	100	100	100	100	100	100	100	100	100	100	100%
48	ByteDance Seed 1.6 Flash	$0.0001	1.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
11	Mistral Small Creative	$0.0000	412ms	100%	100	100	100	100	100	100	100	100	100	100	100%
30	Hermes 3 70B	$0.0000	884ms	100%	100	100	100	100	100	100	100	100	100	100	100%
9	Ministral 3 14B	$0.0000	362ms	100%	100	100	100	100	100	100	100	100	100	100	100%
32	GPT-4.1 Nano	$0.0000	1.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
7	Ministral 3 8B	$0.0000	361ms	100%	100	100	100	100	100	100	100	100	100	100	100%
76	Claude 3 Haiku	$0.0000	5.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
51	Arcee AI: Trinity Mini	$0.0001	2.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
1	Gemma 3 4B	$0.0000	221ms	100%	100	100	100	100	100	100	100	100	100	100	100%
4	Ministral 3 3B	$0.0000	293ms	100%	100	100	100	100	100	100	100	100	100	100	100%
16	Mistral NeMO	$0.0000	536ms	100%	100	100	100	100	100	100	100	100	100	100	100%
3	Ministral 8B	$0.0000	256ms	100%	100	100	100	100	100	100	100	100	100	100	100%
5	Llama 3.1 8B	$0.0000	308ms	100%	100	100	100	100	100	100	100	100	100	100	100%
2	Ministral 3B	$0.0000	273ms	100%	100	100	100	100	100	100	100	100	100	100	100%
21	LFM2 24B	$0.0000	733ms	100%	100	100	100	100	100	100	100	100	100	100	100%
117	Grok 4.20 (Beta, Reasoning)	$0.0031	14.4s	54%	100	100	100	100	100	100	100	50	50	50	85%
105	Llama 3.1 Nemotron 70B	$0.0000	554ms	54%	100	100	100	100	100	100	100	50	50	50	85%
107	Cohere Command R+ (Aug. 2024)	$0.0002	329ms	54%	100	100	100	100	100	100	100	50	50	50	85%
109	Rocinante 12B	$0.0000	3.0s	54%	100	100	100	100	100	100	100	50	50	50	85%
116	Gemini 2.5 Flash (Reasoning)	$0.0019	4.7s	20%	100	100	100	100	100	100	100	100	0	0	80%
115	WizardLM 2 8x22b	$0.0001	7.1s	26%	100	100	100	100	50	50	50	50	50	50	70%
118	Mistral Large	$0.0012	6.2s	27%	100	100	100	50	50	50	50	50	50	50	65%
98.77%