Görsel / multimodal Benchmark Leaderboard | YapayTrend

NEDEN ÖNEMLİ?

Kurumsal copilotta faturalar, raporlar, ekranlar ve dashboard görüntüleri sık kullanılır. Text-only başarı, bu işlerde yeterli değildir.

NASIL OKUNMALI?

Görsel skoru yüksek modelleri doküman otomasyonu, screenshot analizi, tasarımdan koda üretim ve OCR ağırlıklı işlerde kısa listeye alın.

SINIRLAMA

Her model görsel input desteklemez. Office dokümanları, el yazısı ve taranmış PDF gibi gerçek dünya formatlarında benchmark kapsamı hala sınırlıdır.

Genel skora yaklaşık %12 etkiMMMU-ProOfficeQA ProOCRBench V2Design2Code / Vision2WebBenchLM kaynağı

BU KATEGORİDE ÖNE ÇIKANLAR

#1OpenAI

GPT-5.4 Pro100

#2Google

Gemini 3 Pro Deep Think100

#3Anthropic

Claude Mythos 598,9

#4xAI

Grok 4.197,8

#5OpenAI

GPT-5.196,3

VISION / DOCUMENT / GROUNDED

Görsel ve grounded benchmark rehberi

Modelin ekran görüntüsü, grafik, tablo, PDF, taranmış doküman ve görsel-metin karışık iş akışlarını anlayıp yanıtlayabilmesini ölçer.

AĞIRLIK / TİP

Genel skora yaklaşık %12 etki

Neden önemli?

Kurumsal copilotta faturalar, raporlar, ekranlar ve dashboard görüntüleri sık kullanılır. Text-only başarı, bu işlerde yeterli değildir.

Nasıl okunmalı?

Görsel skoru yüksek modelleri doküman otomasyonu, screenshot analizi, tasarımdan koda üretim ve OCR ağırlıklı işlerde kısa listeye alın.

Sınırlama

Her model görsel input desteklemez. Office dokümanları, el yazısı ve taranmış PDF gibi gerçek dünya formatlarında benchmark kapsamı hala sınırlıdır.

MMMU-ProOfficeQA ProOCRBench V2Design2Code / Vision2WebDetay sayfası Kaynak

Ajan görevleri Kodlama Görsel / multimodal Muhakeme Bilgi Talimat takibi Çok dilli Matematik Bağlam

100

En Yüksek Skor

59.5

Ortalama Skor

107

Model Sayısı

Sağlayıcı

#	Model	Sağlayıcı	Görsel / multimodal	Ajan	Kod	Görsel	Bağlam	Fiyat I/O	Kaynak
1	GPT-5.4 Pro	OpenAI	100	89.6	90.6	100	1.1M	$30 / $180	June 16, 2
2	Gemini 3 Pro Deep Think	Google	100	93.3	73.4	100	2M	API	June 16, 2
3	Claude Mythos 5	Anthropic	98.9	100	100	98.9	1M	$10 / $50	June 16, 2
4	Grok 4.1	xAI	97.8	76.6	81.7	97.8	1M	API	June 16, 2
5	GPT-5.1	OpenAI	96.3	73.7	76	96.3	400K	$1.25 / $10	June 16, 2
6	GPT-5.3 Codex	OpenAI	95.8	77.1	87.1	95.8	400K	$1.75 / $14	June 16, 2
7	Claude Sonnet 4.5	Anthropic	94.8	53.8	78.4	94.8	1M	$3 / $15	June 16, 2
8	GPT-5 (high)	OpenAI	93.3	74.5	69.7	93.3	128K	$1.25 / $10	June 16, 2
9	GPT-5 (medium)	OpenAI	90.6	67.7	77.7	90.6	400K	$1.25 / $10	June 16, 2
10	GPT-5.1-Codex-Max	OpenAI	90.1	75.5	75.2	90.1	400K	$1.25 / $10	June 16, 2
11	Grok 4.1 Fast	xAI	89.7	61.1	59.8	89.7	1M	$0.2 / $0.5	June 16, 2
12	GPT-5.2-Codex	OpenAI	89	77.5	77.5	89	400K	$1.75 / $14	June 16, 2
13	Claude Sonnet 4.6	Anthropic	86.2	78.5	82	86.2	1M	$3 / $15	June 16, 2
14	Gemini 2.5 Pro	Google	85.2	57.2	48.5	85.2	1.0M	$1.25 / $10	June 16, 2
15	Gemini 3.1 Pro	Google	84	81.3	93	84	1M	$2 / $12	June 16, 2
16	GPT-5.2	OpenAI	81.5	59.2	78.7	81.5	400K	$1.75 / $14	June 16, 2
17	Gemini 3 Pro	Google	81.2	70.4	72.4	81.2	2M	$2 / $12	June 16, 2
18	Gemini 3.5 Flash	Google	80	94.5	77.3	80	1.0M	$1.5 / $9	June 16, 2
19	Claude Fable 5	Anthropic	79	100	100	79	1M	$10 / $50	June 16, 2
20	Claude 4.1 Opus	Anthropic	77.3	38.6	56.4	77.3	200K	$15 / $75	June 16, 2
21	Claude Opus 4.6	Anthropic	76.7	80.9	85.5	76.7	1M	$5 / $25	June 16, 2
22	Qwen3.7 Plus	Alibaba	76	84.8	87.7	76	1M	$0.32 / $1.28	June 16, 2
23	Claude 4 Sonnet	Anthropic	75.5	43.6	53.4	75.5	200K	$3 / $15	June 16, 2
24	Claude Haiku 4.5	Anthropic	73.6	44.1	53.2	73.6	200K	$1 / $5	June 16, 2
25	Grok 4	xAI	73	52.8	76	73	128K	API	June 16, 2
26	GLM-5 (Reasoning)	Z.AI	72.6	77	69.1	72.6	200K	$1 / $3.2	June 16, 2
27	Gemini 3 Flash	Google	72	44.3	47.5	72	1M	$0.5 / $3	June 16, 2
28	Qwen3.6 Plus	Alibaba	71.6	55.4	77.7	71.6	1M	$0.325 / $1.95	June 16, 2
29	Kimi K2.6	Moonshot AI	71.3	82	89.8	71.3	262K	$0.68 / $3.41	June 16, 2
30	MiMo-V2-Flash	Xiaomi	68.7	56.9	68.6	68.7	256K	Ücretsiz	June 16, 2
31	Kimi K2.5 (Reasoning)	Moonshot AI	67.8	61.9	85	67.8	128K	$0.6 / $3	June 16, 2
32	Mistral Large 3	Mistral	67.7	37.2	37.5	67.7	128K	$0.5 / $1.5	June 16, 2
33	o1-preview	OpenAI	67.5	87.1	78.8	67.5	200K	$15 / $60	June 16, 2
34	Claude 3.5 Sonnet	Anthropic	66.9	38.1	40.3	66.9	200K	$3 / $15	June 16, 2
35	Claude Opus 4.8	Anthropic	66.4	96	98	66.4	1M	$5 / $25	June 16, 2
36	Claude 4.1 Opus Thinking	Anthropic	65.7	24.7	51.3	65.7	200K	API	June 16, 2
37	o3-mini	OpenAI	65.6	61.3	49.4	65.6	200K	$1.1 / $4.4	June 16, 2
38	Gemini 1.5 Pro	Google	65.5	33.6	14.9	65.5	2M	$1.25 / $5	June 16, 2
39	Qwen3.5-122B-A10B	Alibaba	65.2	55.2	70.7	65.2	262K	$0.26 / $2.08	June 16, 2
40	Qwen3.5 397B	Alibaba	65.1	53.4	67.5	65.1	128K	$0.6 / $3.6	June 16, 2
41	Qwen3.5-27B	Alibaba	65.1	50.2	70.3	65.1	262K	$0.195 / $1.56	June 16, 2
42	Qwen3.6-27B	Alibaba	65	68.7	77.9	65	262K	$0.2885 / $3.17	June 16, 2
43	o3-pro	OpenAI	64.7	60.9	54.5	64.7	200K	$20 / $80	June 16, 2
44	Qwen3.6-35B-A3B	Alibaba	64	53.1	72.2	64	262K	$0.15 / $1	June 16, 2
45	GPT-4.1	OpenAI	63.9	55.2	54.6	63.9	1.0M	$2 / $8	June 16, 2
46	Qwen3.5-35B-A3B	Alibaba	63.3	44.6	59.1	63.3	262K	$0.14 / $1	June 16, 2
47	Kimi K2.5	Moonshot AI	63.1	44.7	81	63.1	262K	$0.375 / $2.025	June 16, 2
48	GPT-4o	OpenAI	62.2	38.6	24.4	62.2	128K	$2.5 / $10	June 16, 2
49	o3	OpenAI	61.7	56.1	65.1	61.7	200K	$2 / $8	June 16, 2
50	Claude Opus 4.5	Anthropic	61.2	73.2	75.6	61.2	200K	$5 / $25	June 16, 2
51	GPT-5.4	OpenAI	59.6	84	87.2	59.6	1.1M	$2.5 / $15	June 16, 2
52	DeepSeek V3.2 (Thinking)	DeepSeek	59	61.1	51.5	59	128K	$0.55 / $2.19	June 16, 2
53	o1	OpenAI	58.9	56	48.2	58.9	200K	$15 / $60	June 16, 2
54	Claude 3 Opus	Anthropic	58.9	33.3	13.4	58.9	200K	$15 / $75	June 16, 2
55	Qwen3.5 397B (Reasoning)	Alibaba	58.4	68.8	85.4	58.4	128K	$0.6 / $3.6	June 16, 2
56	Gemini 3.1 Flash-Lite	Google	58.3	41.1	25.8	58.3	1.0M	$0.25 / $1.5	June 16, 2
57	GLM-4.7	Z.AI	58.2	53.4	72.5	58.2	203K	$0.4 / $1.75	June 16, 2
58	GPT-5.5	OpenAI	58	95.9	82.6	58	1.1M	$5 / $30	June 16, 2
59	GPT-4.1 mini	OpenAI	56.8	43	24.3	56.8	1.0M	$0.4 / $1.6	June 16, 2
60	GLM-5	Z.AI	56	48.1	76.2	56	203K	$0.6 / $1.92	June 16, 2
61	Qwen2.5-1M	Alibaba	54.3	54.2	48.6	54.3	1M	Ücretsiz	June 16, 2
62	Gemini 2.5 Flash	Google	54	32.9	16.5	54	1.0M	$0.3 / $2.5	June 16, 2
63	DeepSeekMath V2	DeepSeek	53.9	53	51.3	53.9	128K	Ücretsiz	June 16, 2
64	Qwen2.5-72B	Alibaba	51.7	46.1	46.8	51.7	128K	Ücretsiz	June 16, 2
65	o4-mini (high)	OpenAI	50.3	38.5	45.5	50.3	200K	$1.1 / $4.4	June 16, 2
66	DeepSeek V3.2	DeepSeek	50	49.8	57.3	50	131K	$0.2288 / $0.3432	June 16, 2
67	MiniMax M3	MiniMax	48.1	85	84.6	48.1	1.0M	$0.3 / $1.2	June 16, 2
68	Grok 4.20	xAI	47.6	54.2	76.4	47.6	2M	$1.25 / $2.5	June 16, 2
69	DeepSeek LLM 2.0	DeepSeek	47.5	49.1	45.6	47.5	128K	Ücretsiz	June 16, 2
70	Claude Opus 4.7 (Adaptive)	Anthropic	45	85.6	93.5	45	1M	$5 / $25	June 16, 2
71	Llama 3.1 405B	Meta	43.8	31.2	36.5	43.8	128K	Ücretsiz	June 16, 2
72	GPT-4o mini	OpenAI	41.2	38.5	90.9	41.2	128K	$0.15 / $0.6	June 16, 2
73	Mistral Large 2	Mistral	41.1	32.3	32.6	41.1	128K	API	June 16, 2
74	Nemotron 3 Super 100B	NVIDIA	40	43.3	43	40	1M	Ücretsiz	June 16, 2
75	GPT-4.1 nano	OpenAI	37.9	22.7	8.7	37.9	1.0M	$0.1 / $0.4	June 16, 2
76	Llama 4 Scout	Meta	36.4	17.1	-	36.4	10M	$0.1 / $0.3	June 16, 2
77	DeepSeek Coder 2.0	DeepSeek	36.2	59.3	60.9	36.2	128K	API	June 16, 2
78	Llama 3 70B	Meta	25.8	21.9	2.6	25.8	128K	Ücretsiz	June 16, 2
79	Grok Code Fast 1	xAI	21.2	39.9	61.6	21.2	256K	$0.2 / $1.5	June 16, 2
80	o1-pro	OpenAI	19.3	16.1	14.5	19.3	200K	$150 / $600	June 16, 2
81	GPT-OSS 120B	OpenAI	18.9	34.3	21.4	18.9	131K	$0.039 / $0.18	June 16, 2
82	Phi-4	Microsoft	18.9	11.5	48.1	18.9	16K	$0.065 / $0.14	June 16, 2
83	DeepSeek-R1	DeepSeek	17	31.1	26.4	17	128K	$0.55 / $2.19	June 16, 2
84	Nemotron 3 Nano 30B	NVIDIA	12.5	19.7	16.8	12.5	32K	Ücretsiz	June 16, 2
85	Grok 3 [Beta]	xAI	9.4	21	28.2	9.4	128K	API	June 16, 2
86	Qwen3 235B 2507 (Reasoning)	Alibaba	7.3	38.7	41.5	7.3	128K	Ücretsiz	June 16, 2
87	Qwen3 235B 2507	Alibaba	6.5	16.3	22.8	6.5	128K	Ücretsiz	June 16, 2
88	DeepSeek V3.1 (Reasoning)	DeepSeek	6.2	32.8	21	6.2	128K	Ücretsiz	June 16, 2
89	GLM-4.5	Z.AI	5.2	22.9	7.8	5.2	131K	$0.6 / $2.2	June 16, 2
90	DeepSeek V3.1	DeepSeek	3.7	25.9	15.9	3.7	164K	$0.21 / $0.79	June 16, 2
91	GLM-5.2	Z.AI	-	100	85.6	-	1.0M	$1.4 / $4.4	June 16, 2
92	Qwen3.7 Max	Alibaba	-	86	91.6	-	1M	$1.25 / $3.75	June 16, 2
93	DeepSeek V4 Pro (Max)	DeepSeek	-	87.1	89.7	-	1M	$1.74 / $3.48	June 16, 2
94	DeepSeek V4 Pro (High)	DeepSeek	-	81.5	86	-	1.0M	$0.435 / $0.87	June 16, 2
95	GLM-5.1	Z.AI	-	66	81.3	-	203K	$0.98 / $3.08	June 16, 2
96	DeepSeek V4 Flash (Max)	DeepSeek	-	68.4	82.2	-	1M	$0.14 / $0.28	June 16, 2
97	DeepSeek V4 Flash (High)	DeepSeek	-	60.1	82.5	-	1M	$0.14 / $0.28	June 16, 2
98	Nemotron 3 Ultra	NVIDIA	-	50.5	80.4	-	1M	$0.5 / $2.2	June 16, 2
99	DeepSeek V4 Pro	DeepSeek	-	65.6	68.4	-	1M	$1.74 / $3.48	June 16, 2
100	MAI-Thinking-1	Microsoft	-	31.2	84.5	-	256K	API	June 16, 2
101	DeepSeek V4 Flash	DeepSeek	-	47.2	62	-	1.0M	$0.09 / $0.18	June 16, 2
102	MiniMax M2.7	MiniMax	-	47.8	54	-	205K	$0.25 / $1	June 16, 2
103	Kimi K2	Moonshot AI	-	30	53.4	-	128K	$0.6 / $2.5	June 16, 2
104	Sarvam 105B	Sarvam	-	28.9	36.9	-	128K	Ücretsiz	June 16, 2
105	DeepSeek V3	DeepSeek	-	-	28.5	-	131K	$0.2002 / $0.8001	June 16, 2
106	MiniCPM5-1B	OpenBMB	-	-	-	-	131K	API	June 16, 2
107	DBRX Instruct	Databricks	-	8.3	60	-	32K	Ücretsiz	June 16, 2

Veriler Supabase kataloğundaki BenchLM.ai ve OpenRouter kayıtlarından okunur. Fiyat ve skorlar sağlayıcı güncellemeleriyle değişebilir. Kaynaklar: BenchLM.ai · OpenRouter

GÖRSEL / MULTİMODAL LEADERBOARD

Görsel ve grounded benchmark rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama