Bağlam Benchmark Leaderboard | YapayTrend

NEDEN ÖNEMLİ?

Bağlam büyük olduğunda daha fazla dosya, doküman veya konuşma geçmişi modele verilebilir. Ancak büyük bağlam her zaman daha iyi muhakeme anlamına gelmez.

NASIL OKUNMALI?

Uzun doküman veya repo analizlerinde bağlamı önceliklendirin; kısa görevlerde ise skor, latency ve fiyat çoğu zaman daha belirleyicidir.

SINIRLAMA

Bağlam limiti sağlayıcıya, ürün katmanına ve API yapılandırmasına göre değişebilir. Büyük bağlam kullanımı token maliyetini artırır.

Skor değil, operasyonel kapasite metriğiContext WindowLong-context retrievalBenchLM kaynağı

BU KATEGORİDE ÖNE ÇIKANLAR

#1Meta

Llama 4 Scout10.000.000

#2Google

Gemini 3 Pro Deep Think2.000.000

#3Google

Gemini 3 Pro2.000.000

#4xAI

Grok 4.202.000.000

#5Google

Gemini 1.5 Pro2.000.000

CONTEXT WINDOW

Bağlam penceresi rehberi

Modelin tek istekte işleyebildiği yaklaşık token kapasitesini gösterir. Uzun doküman, büyük repo ve çok mesajlı analizlerde pratik sınırı belirler.

AĞIRLIK / TİP

Skor değil, operasyonel kapasite metriği

Neden önemli?

Bağlam büyük olduğunda daha fazla dosya, doküman veya konuşma geçmişi modele verilebilir. Ancak büyük bağlam her zaman daha iyi muhakeme anlamına gelmez.

Nasıl okunmalı?

Uzun doküman veya repo analizlerinde bağlamı önceliklendirin; kısa görevlerde ise skor, latency ve fiyat çoğu zaman daha belirleyicidir.

Sınırlama

Bağlam limiti sağlayıcıya, ürün katmanına ve API yapılandırmasına göre değişebilir. Büyük bağlam kullanımı token maliyetini artırır.

Context WindowLong-context retrievalDetay sayfası Kaynak

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

10M

En Geniş Bağlam

620K

Ortalama Bağlam

107

Model Sayısı

Sağlayıcı

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

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

BAĞLAM LEADERBOARD

Bağlam penceresi rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama