Kodlama Benchmark Leaderboard | YapayTrend

NEDEN ÖNEMLİ?

Kod asistanı, repo inceleme, test yazma, refactor ve otomatik PR akışlarında doğru model seçmek için en doğrudan sinyaldir.

NASIL OKUNMALI?

Kodlama skorunu bağlam penceresi ve maliyetle birlikte okuyun. Büyük repo işlerinde daha geniş bağlam, küçük görevlerde ise düşük gecikme ve fiyat daha önemli olabilir.

SINIRLAMA

HumanEval gibi eski testler frontier modellerde doygunlaştı. Daha güvenilir sinyal için SWE-bench Pro ve sürekli güncellenen LiveCodeBench gibi daha zor ve taze testler öne çıkarılmalı.

Genel skora yaklaşık %20 etkiSWE-bench ProLiveCodeBenchSWE-RebenchReact Native EvalsBenchLM kaynağı

BU KATEGORİDE ÖNE ÇIKANLAR

#1Anthropic

Claude Mythos 5100

#2Anthropic

Claude Fable 5100

#3Anthropic

Claude Opus 4.898

#4Anthropic

Claude Opus 4.7 (Adaptive)93,5

#5Google

Gemini 3.1 Pro93

SWE-BENCH / LIVECODEBENCH

Kodlama benchmark rehberi

Modelin gerçek yazılım hatalarını çözme, rekabetçi programlama problemlerini anlama ve çok dosyalı kod bağlamında doğru değişiklik yapma performansını ölçer.

AĞIRLIK / TİP

Genel skora yaklaşık %20 etki

Neden önemli?

Kod asistanı, repo inceleme, test yazma, refactor ve otomatik PR akışlarında doğru model seçmek için en doğrudan sinyaldir.

Nasıl okunmalı?

Kodlama skorunu bağlam penceresi ve maliyetle birlikte okuyun. Büyük repo işlerinde daha geniş bağlam, küçük görevlerde ise düşük gecikme ve fiyat daha önemli olabilir.

Sınırlama

HumanEval gibi eski testler frontier modellerde doygunlaştı. Daha güvenilir sinyal için SWE-bench Pro ve sürekli güncellenen LiveCodeBench gibi daha zor ve taze testler öne çıkarılmalı.

SWE-bench ProLiveCodeBenchSWE-RebenchReact Native EvalsDetay sayfası Kaynak

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

100

En Yüksek Skor

60.5

Ortalama Skor

107

Model Sayısı

Sağlayıcı

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

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

KODLAMA LEADERBOARD

Kodlama benchmark rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama