AI Model Leaderboard | YapayTrend

TOOL USE / BROWSER / COMPUTER USE

Ajan görevleri benchmark rehberi

Bir modelin sadece cevap yazmasını değil; terminal, tarayıcı, araç çağırma ve çok adımlı iş akışlarında işi tamamlayıp tamamlayamadığını ölçer.

AĞIRLIK / TİP

Genel skora yaklaşık %22 etki

Neden önemli?

Ürün içinde araştırma ajanı, kod ajanı, veri ajanı veya operasyon asistanı çalıştıracaksanız en kritik sinyal budur. Modelin uzun aksiyon zincirinde bağlamı kaybetmemesi ve doğru aracı seçmesi gerekir.

Nasıl okunmalı?

Ajan skorunu tek başına değil; gecikme, token maliyeti, tool-use güvenliği ve loglanabilirlik ile birlikte değerlendirin. En yüksek skor, her zaman en ekonomik üretim seçeneği değildir.

Sınırlama

Ajan benchmarkları hala yeni ve farklı test altyapıları kullanıyor. Bazı modellerde veri eksik olduğu için sıralama dışı kalabilir; bu boşluklar tahmini skorla doldurulmamalıdır.

Terminal-Bench 2.0BrowseCompOSWorld-VerifiedMCP AtlasDetay sayfası Kaynak

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

En Yüksek Skor

59.8

Ortalama Skor

107

Model Sayısı

Sağlayıcı

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

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

AI MODELLEADERBOARDCANLI

Ajan görevleri benchmark rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama