Talimat takibi Benchmark Leaderboard | YapayTrend

NEDEN ÖNEMLİ?

Otomasyon pipeline’larında JSON şeması, tablo formatı, kısa cevap veya güvenlik talimatı ihlali doğrudan ürün hatasına dönüşür.

NASIL OKUNMALI?

Structured output, içerik ajanı ve workflow otomasyonlarında bu skoru özellikle kontrol edin. Yüksek genel skor, talimat uyumu garantisi değildir.

SINIRLAMA

IFEval doğrulanabilir sınırlı talimat setlerini ölçer; nüanslı veya belirsiz insan yönergelerindeki kaliteyi tam temsil etmez.

Genel skora yaklaşık %5 etkiIFEvalIFBenchBenchLM kaynağı

BU KATEGORİDE ÖNE ÇIKANLAR

#1Microsoft

MAI-Thinking-1100

#2Moonshot AI

Kimi K2.5 (Reasoning)98,9

#3OpenAI

GPT-5.496

#4NVIDIA

Nemotron 3 Ultra96

#5Alibaba

Qwen3.7 Plus95,6

IFEVAL / IFBENCH

Talimat takibi benchmark rehberi

Modelin format, kelime sayısı, zorunlu alan, yasaklı ifade, sıralama ve çıktı şeması gibi açık talimatlara uyup uymadığını ölçer.

AĞIRLIK / TİP

Genel skora yaklaşık %5 etki

Neden önemli?

Otomasyon pipeline’larında JSON şeması, tablo formatı, kısa cevap veya güvenlik talimatı ihlali doğrudan ürün hatasına dönüşür.

Nasıl okunmalı?

Structured output, içerik ajanı ve workflow otomasyonlarında bu skoru özellikle kontrol edin. Yüksek genel skor, talimat uyumu garantisi değildir.

Sınırlama

IFEval doğrulanabilir sınırlı talimat setlerini ölçer; nüanslı veya belirsiz insan yönergelerindeki kaliteyi tam temsil etmez.

IFEvalIFBenchDetay sayfası Kaynak

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

100

En Yüksek Skor

70.7

Ortalama Skor

107

Model Sayısı

Sağlayıcı

#	Model	Sağlayıcı	Talimat takibi	Ajan	Kod	Görsel	Bağlam	Fiyat I/O	Kaynak
1	MAI-Thinking-1	Microsoft	100	31.2	84.5	-	256K	API	June 16, 2
2	Kimi K2.5 (Reasoning)	Moonshot AI	98.9	61.9	85	67.8	128K	$0.6 / $3	June 16, 2
3	GPT-5.4	OpenAI	96	84	87.2	59.6	1.1M	$2.5 / $15	June 16, 2
4	Nemotron 3 Ultra	NVIDIA	96	50.5	80.4	-	1M	$0.5 / $2.2	June 16, 2
5	Qwen3.7 Plus	Alibaba	95.6	84.8	87.7	76	1M	$0.32 / $1.28	June 16, 2
6	Grok 4.20	xAI	95.4	54.2	76.4	47.6	2M	$1.25 / $2.5	June 16, 2
7	Claude Opus 4.6	Anthropic	95.3	80.9	85.5	76.7	1M	$5 / $25	June 16, 2
8	GLM-5.1	Z.AI	93.8	66	81.3	-	203K	$0.98 / $3.08	June 16, 2
9	GPT-5.4 Pro	OpenAI	93.7	89.6	90.6	100	1.1M	$30 / $180	June 16, 2
10	Gemini 3.1 Pro	Google	93.4	81.3	93	84	1M	$2 / $12	June 16, 2
11	Qwen3.7 Max	Alibaba	93.4	86	91.6	-	1M	$1.25 / $3.75	June 16, 2
12	Claude Fable 5	Anthropic	92.7	100	100	79	1M	$10 / $50	June 16, 2
13	o1	OpenAI	92.3	56	48.2	58.9	200K	$15 / $60	June 16, 2
14	Qwen3.6 Plus	Alibaba	91.8	55.4	77.7	71.6	1M	$0.325 / $1.95	June 16, 2
15	GPT-5.2-Codex	OpenAI	91.6	77.5	77.5	89	400K	$1.75 / $14	June 16, 2
16	Claude Mythos 5	Anthropic	91.4	100	100	98.9	1M	$10 / $50	June 16, 2
17	GPT-5.3 Codex	OpenAI	91.4	77.1	87.1	95.8	400K	$1.75 / $14	June 16, 2
18	Grok 4.1	xAI	90.6	76.6	81.7	97.8	1M	API	June 16, 2
19	Qwen3.5-27B	Alibaba	89	50.2	70.3	65.1	262K	$0.195 / $1.56	June 16, 2
20	GPT-5.1-Codex-Max	OpenAI	87.9	75.5	75.2	90.1	400K	$1.25 / $10	June 16, 2
21	Qwen3.5-122B-A10B	Alibaba	87.8	55.2	70.7	65.2	262K	$0.26 / $2.08	June 16, 2
22	o3-mini	OpenAI	85.3	61.3	49.4	65.6	200K	$1.1 / $4.4	June 16, 2
23	GPT-5.2	OpenAI	84.9	59.2	78.7	81.5	400K	$1.75 / $14	June 16, 2
24	Qwen3.5 397B	Alibaba	84.8	53.4	67.5	65.1	128K	$0.6 / $3.6	June 16, 2
25	Kimi K2.5	Moonshot AI	84.5	44.7	81	63.1	262K	$0.375 / $2.025	June 16, 2
26	GLM-5	Z.AI	84.3	48.1	76.2	56	203K	$0.6 / $1.92	June 16, 2
27	Claude Sonnet 4.5	Anthropic	84.2	53.8	78.4	94.8	1M	$3 / $15	June 16, 2
28	Kimi K2	Moonshot AI	83.5	30	53.4	-	128K	$0.6 / $2.5	June 16, 2
29	Claude Sonnet 4.6	Anthropic	82.7	78.5	82	86.2	1M	$3 / $15	June 16, 2
30	Gemini 3 Pro Deep Think	Google	81.6	93.3	73.4	100	2M	API	June 16, 2
31	Qwen3.5-35B-A3B	Alibaba	81.2	44.6	59.1	63.3	262K	$0.14 / $1	June 16, 2
32	GLM-5 (Reasoning)	Z.AI	81	77	69.1	72.6	200K	$1 / $3.2	June 16, 2
33	GPT-5 (high)	OpenAI	80.7	74.5	69.7	93.3	128K	$1.25 / $10	June 16, 2
34	Qwen3.5 397B (Reasoning)	Alibaba	80.6	68.8	85.4	58.4	128K	$0.6 / $3.6	June 16, 2
35	Grok 4.1 Fast	xAI	79.7	61.1	59.8	89.7	1M	$0.2 / $0.5	June 16, 2
36	Gemini 3 Pro	Google	79.5	70.4	72.4	81.2	2M	$2 / $12	June 16, 2
37	Qwen3 235B 2507	Alibaba	79.5	16.3	22.8	6.5	128K	Ücretsiz	June 16, 2
38	GPT-4.1 mini	OpenAI	78.8	43	24.3	56.8	1.0M	$0.4 / $1.6	June 16, 2
39	Gemini 3.5 Flash	Google	78	94.5	77.3	80	1.0M	$1.5 / $9	June 16, 2
40	o1-preview	OpenAI	76.9	87.1	78.8	67.5	200K	$15 / $60	June 16, 2
41	GPT-5 (medium)	OpenAI	76.9	67.7	77.7	90.6	400K	$1.25 / $10	June 16, 2
42	Claude 4.1 Opus Thinking	Anthropic	76.9	24.7	51.3	65.7	200K	API	June 16, 2
43	MiniMax M2.7	MiniMax	76.3	47.8	54	-	205K	$0.25 / $1	June 16, 2
44	Qwen3 235B 2507 (Reasoning)	Alibaba	76.2	38.7	41.5	7.3	128K	Ücretsiz	June 16, 2
45	GPT-5.1	OpenAI	75.8	73.7	76	96.3	400K	$1.25 / $10	June 16, 2
46	GPT-4.1	OpenAI	74.7	55.2	54.6	63.9	1.0M	$2 / $8	June 16, 2
47	GLM-4.7	Z.AI	72.9	53.4	72.5	58.2	203K	$0.4 / $1.75	June 16, 2
48	Claude Haiku 4.5	Anthropic	69.6	44.1	53.2	73.6	200K	$1 / $5	June 16, 2
49	DeepSeek Coder 2.0	DeepSeek	69.6	59.3	60.9	36.2	128K	API	June 16, 2
50	Llama 3.1 405B	Meta	69.6	31.2	36.5	43.8	128K	Ücretsiz	June 16, 2
51	Mistral Large 3	Mistral	67	37.2	37.5	67.7	128K	$0.5 / $1.5	June 16, 2
52	Gemini 3 Flash	Google	66.9	44.3	47.5	72	1M	$0.5 / $3	June 16, 2
53	o3	OpenAI	65.9	56.1	65.1	61.7	200K	$2 / $8	June 16, 2
54	DeepSeek LLM 2.0	DeepSeek	65.9	49.1	45.6	47.5	128K	Ücretsiz	June 16, 2
55	Qwen2.5-72B	Alibaba	65.9	46.1	46.8	51.7	128K	Ücretsiz	June 16, 2
56	Sarvam 105B	Sarvam	65.2	28.9	36.9	-	128K	Ücretsiz	June 16, 2
57	Claude Opus 4.5	Anthropic	63.2	73.2	75.6	61.2	200K	$5 / $25	June 16, 2
58	MiMo-V2-Flash	Xiaomi	62.3	56.9	68.6	68.7	256K	Ücretsiz	June 16, 2
59	Qwen2.5-1M	Alibaba	62.3	54.2	48.6	54.3	1M	Ücretsiz	June 16, 2
60	Nemotron 3 Super 100B	NVIDIA	62.3	43.3	43	40	1M	Ücretsiz	June 16, 2
61	DeepSeek V3.2 (Thinking)	DeepSeek	62.1	61.1	51.5	59	128K	$0.55 / $2.19	June 16, 2
62	DeepSeek V3.2	DeepSeek	61.7	49.8	57.3	50	131K	$0.2288 / $0.3432	June 16, 2
63	DeepSeek V3	DeepSeek	61.2	-	28.5	-	131K	$0.2002 / $0.8001	June 16, 2
64	GPT-4.1 nano	OpenAI	59.3	22.7	8.7	37.9	1.0M	$0.1 / $0.4	June 16, 2
65	Gemini 2.5 Pro	Google	59	57.2	48.5	85.2	1.0M	$1.25 / $10	June 16, 2
66	Claude 4.1 Opus	Anthropic	58.6	38.6	56.4	77.3	200K	$15 / $75	June 16, 2
67	Claude 4 Sonnet	Anthropic	58.6	43.6	53.4	75.5	200K	$3 / $15	June 16, 2
68	DeepSeekMath V2	DeepSeek	58.6	53	51.3	53.9	128K	Ücretsiz	June 16, 2
69	o4-mini (high)	OpenAI	58.6	38.5	45.5	50.3	200K	$1.1 / $4.4	June 16, 2
70	Claude 3.5 Sonnet	Anthropic	58.6	38.1	40.3	66.9	200K	$3 / $15	June 16, 2
71	Grok 4	xAI	54.9	52.8	76	73	128K	API	June 16, 2
72	o3-pro	OpenAI	54.9	60.9	54.5	64.7	200K	$20 / $80	June 16, 2
73	GPT-4o	OpenAI	54.9	38.6	24.4	62.2	128K	$2.5 / $10	June 16, 2
74	DeepSeek-R1	DeepSeek	54.6	31.1	26.4	17	128K	$0.55 / $2.19	June 16, 2
75	Mistral Large 2	Mistral	50.6	32.3	32.6	41.1	128K	API	June 16, 2
76	Gemini 3.1 Flash-Lite	Google	44	41.1	25.8	58.3	1.0M	$0.25 / $1.5	June 16, 2
77	Grok Code Fast 1	xAI	44	39.9	61.6	21.2	256K	$0.2 / $1.5	June 16, 2
78	Gemini 2.5 Flash	Google	41.8	32.9	16.5	54	1.0M	$0.3 / $2.5	June 16, 2
79	Nemotron 3 Nano 30B	NVIDIA	40.3	19.7	16.8	12.5	32K	Ücretsiz	June 16, 2
80	GPT-OSS 120B	OpenAI	38.5	34.3	21.4	18.9	131K	$0.039 / $0.18	June 16, 2
81	Gemini 1.5 Pro	Google	36.6	33.6	14.9	65.5	2M	$1.25 / $5	June 16, 2
82	Claude 3 Opus	Anthropic	36.6	33.3	13.4	58.9	200K	$15 / $75	June 16, 2
83	Llama 3 70B	Meta	36.6	21.9	2.6	25.8	128K	Ücretsiz	June 16, 2
84	MiniCPM5-1B	OpenBMB	31.9	-	-	-	131K	API	June 16, 2
85	Llama 4 Scout	Meta	18.8	17.1	-	36.4	10M	$0.1 / $0.3	June 16, 2
86	DeepSeek V3.1 (Reasoning)	DeepSeek	14.1	32.8	21	6.2	128K	Ücretsiz	June 16, 2
87	GLM-4.5	Z.AI	8.5	22.9	7.8	5.2	131K	$0.6 / $2.2	June 16, 2
88	GLM-5.2	Z.AI	-	100	85.6	-	1.0M	$1.4 / $4.4	June 16, 2
89	Claude Opus 4.8	Anthropic	-	96	98	66.4	1M	$5 / $25	June 16, 2
90	GPT-5.5	OpenAI	-	95.9	82.6	58	1.1M	$5 / $30	June 16, 2
91	DeepSeek V4 Pro (Max)	DeepSeek	-	87.1	89.7	-	1M	$1.74 / $3.48	June 16, 2
92	Claude Opus 4.7 (Adaptive)	Anthropic	-	85.6	93.5	45	1M	$5 / $25	June 16, 2
93	DeepSeek V4 Pro (High)	DeepSeek	-	81.5	86	-	1.0M	$0.435 / $0.87	June 16, 2
94	Kimi K2.6	Moonshot AI	-	82	89.8	71.3	262K	$0.68 / $3.41	June 16, 2
95	MiniMax M3	MiniMax	-	85	84.6	48.1	1.0M	$0.3 / $1.2	June 16, 2
96	DeepSeek V4 Flash (Max)	DeepSeek	-	68.4	82.2	-	1M	$0.14 / $0.28	June 16, 2
97	Qwen3.6-27B	Alibaba	-	68.7	77.9	65	262K	$0.2885 / $3.17	June 16, 2
98	DeepSeek V4 Flash (High)	DeepSeek	-	60.1	82.5	-	1M	$0.14 / $0.28	June 16, 2
99	DeepSeek V4 Pro	DeepSeek	-	65.6	68.4	-	1M	$1.74 / $3.48	June 16, 2
100	Qwen3.6-35B-A3B	Alibaba	-	53.1	72.2	64	262K	$0.15 / $1	June 16, 2
101	DeepSeek V4 Flash	DeepSeek	-	47.2	62	-	1.0M	$0.09 / $0.18	June 16, 2
102	GPT-4o mini	OpenAI	-	38.5	90.9	41.2	128K	$0.15 / $0.6	June 16, 2
103	DBRX Instruct	Databricks	-	8.3	60	-	32K	Ücretsiz	June 16, 2
104	Grok 3 [Beta]	xAI	-	21	28.2	9.4	128K	API	June 16, 2
105	o1-pro	OpenAI	-	16.1	14.5	19.3	200K	$150 / $600	June 16, 2
106	Phi-4	Microsoft	-	11.5	48.1	18.9	16K	$0.065 / $0.14	June 16, 2
107	DeepSeek V3.1	DeepSeek	-	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

TALİMAT TAKİBİ LEADERBOARD

Talimat takibi benchmark rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama