Matematik Benchmark Leaderboard | YapayTrend

NEDEN ÖNEMLİ?

Finans, veri analizi, optimizasyon, mühendislik ve eğitim senaryolarında aritmetik doğruluk kadar çözüm yolunun tutarlılığı da kritiktir.

NASIL OKUNMALI?

Matematik kritikse explicit reasoning destekli modelleri, maliyet ve gecikme etkisini de hesaba katarak değerlendirin.

SINIRLAMA

AIME ve HMMT gibi yarışma testleri en üst modellerde doygunlaştı. Daha ayrıştırıcı sinyal için BRUMO ve MATH-500 gibi testlere bakılmalı.

Genel skora yaklaşık %5 etkiBRUMOMATH-500AIME / HMMTBenchLM kaynağı

BU KATEGORİDE ÖNE ÇIKANLAR

#1OpenAI

GPT-5.3 Codex100

#2xAI

Grok 4.199,4

#3Microsoft

MAI-Thinking-198,4

#4OpenAI

GPT-5.2-Codex97,7

#5OpenAI

GPT-5.1-Codex-Max97,2

BRUMO / MATH-500 / AIME

Matematik benchmark rehberi

Modelin sayısal akıl yürütme, ispat benzeri adımlar, yarışma matematiği ve zor problem çözme kabiliyetini ölçer.

AĞIRLIK / TİP

Genel skora yaklaşık %5 etki

Neden önemli?

Finans, veri analizi, optimizasyon, mühendislik ve eğitim senaryolarında aritmetik doğruluk kadar çözüm yolunun tutarlılığı da kritiktir.

Nasıl okunmalı?

Matematik kritikse explicit reasoning destekli modelleri, maliyet ve gecikme etkisini de hesaba katarak değerlendirin.

Sınırlama

AIME ve HMMT gibi yarışma testleri en üst modellerde doygunlaştı. Daha ayrıştırıcı sinyal için BRUMO ve MATH-500 gibi testlere bakılmalı.

BRUMOMATH-500AIME / HMMTDetay sayfası Kaynak

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

100

En Yüksek Skor

65.5

Ortalama Skor

107

Model Sayısı

Sağlayıcı

#	Model	Sağlayıcı	Matematik	Ajan	Kod	Görsel	Bağlam	Fiyat I/O	Kaynak
1	GPT-5.3 Codex	OpenAI	100	77.1	87.1	95.8	400K	$1.75 / $14	June 16, 2
2	Grok 4.1	xAI	99.4	76.6	81.7	97.8	1M	API	June 16, 2
3	MAI-Thinking-1	Microsoft	98.4	31.2	84.5	-	256K	API	June 16, 2
4	GPT-5.2-Codex	OpenAI	97.7	77.5	77.5	89	400K	$1.75 / $14	June 16, 2
5	GPT-5.1-Codex-Max	OpenAI	97.2	75.5	75.2	90.1	400K	$1.25 / $10	June 16, 2
6	GPT-5.5	OpenAI	96.4	95.9	82.6	58	1.1M	$5 / $30	June 16, 2
7	Claude Opus 4.5	Anthropic	94.9	73.2	75.6	61.2	200K	$5 / $25	June 16, 2
8	Gemini 3 Pro Deep Think	Google	94.8	93.3	73.4	100	2M	API	June 16, 2
9	GPT-5.4	OpenAI	94.4	84	87.2	59.6	1.1M	$2.5 / $15	June 16, 2
10	o1-preview	OpenAI	94.1	87.1	78.8	67.5	200K	$15 / $60	June 16, 2
11	Grok 4.1 Fast	xAI	93.7	61.1	59.8	89.7	1M	$0.2 / $0.5	June 16, 2
12	GPT-5.4 Pro	OpenAI	92.8	89.6	90.6	100	1.1M	$30 / $180	June 16, 2
13	Qwen3.5 397B (Reasoning)	Alibaba	92.3	68.8	85.4	58.4	128K	$0.6 / $3.6	June 16, 2
14	GLM-5 (Reasoning)	Z.AI	92.2	77	69.1	72.6	200K	$1 / $3.2	June 16, 2
15	GPT-5 (medium)	OpenAI	91.7	67.7	77.7	90.6	400K	$1.25 / $10	June 16, 2
16	GLM-5.1	Z.AI	91.3	66	81.3	-	203K	$0.98 / $3.08	June 16, 2
17	GLM-5	Z.AI	91.3	48.1	76.2	56	203K	$0.6 / $1.92	June 16, 2
18	Sarvam 105B	Sarvam	90.4	28.9	36.9	-	128K	Ücretsiz	June 16, 2
19	Claude Sonnet 4.5	Anthropic	87.7	53.8	78.4	94.8	1M	$3 / $15	June 16, 2
20	o3-pro	OpenAI	86.4	60.9	54.5	64.7	200K	$20 / $80	June 16, 2
21	Claude Opus 4.6	Anthropic	86.3	80.9	85.5	76.7	1M	$5 / $25	June 16, 2
22	o3	OpenAI	83.4	56.1	65.1	61.7	200K	$2 / $8	June 16, 2
23	MiMo-V2-Flash	Xiaomi	82.1	56.9	68.6	68.7	256K	Ücretsiz	June 16, 2
24	GPT-5.2	OpenAI	80.9	59.2	78.7	81.5	400K	$1.75 / $14	June 16, 2
25	Gemini 3 Pro	Google	80.3	70.4	72.4	81.2	2M	$2 / $12	June 16, 2
26	Grok 4	xAI	80	52.8	76	73	128K	API	June 16, 2
27	GLM-4.7	Z.AI	78.2	53.4	72.5	58.2	203K	$0.4 / $1.75	June 16, 2
28	Phi-4	Microsoft	78.1	11.5	48.1	18.9	16K	$0.065 / $0.14	June 16, 2
29	Qwen2.5-1M	Alibaba	76.9	54.2	48.6	54.3	1M	Ücretsiz	June 16, 2
30	Qwen2.5-72B	Alibaba	76.2	46.1	46.8	51.7	128K	Ücretsiz	June 16, 2
31	Claude Sonnet 4.6	Anthropic	75.7	78.5	82	86.2	1M	$3 / $15	June 16, 2
32	DeepSeekMath V2	DeepSeek	74.7	53	51.3	53.9	128K	Ücretsiz	June 16, 2
33	Gemini 2.5 Pro	Google	73.5	57.2	48.5	85.2	1.0M	$1.25 / $10	June 16, 2
34	Qwen3.5 397B	Alibaba	73.3	53.4	67.5	65.1	128K	$0.6 / $3.6	June 16, 2
35	Claude Opus 4.7 (Adaptive)	Anthropic	71.2	85.6	93.5	45	1M	$5 / $25	June 16, 2
36	DeepSeek Coder 2.0	DeepSeek	70.9	59.3	60.9	36.2	128K	API	June 16, 2
37	DeepSeek LLM 2.0	DeepSeek	70.8	49.1	45.6	47.5	128K	Ücretsiz	June 16, 2
38	DeepSeek V3.2	DeepSeek	70.5	49.8	57.3	50	131K	$0.2288 / $0.3432	June 16, 2
39	GPT-5 (high)	OpenAI	70.2	74.5	69.7	93.3	128K	$1.25 / $10	June 16, 2
40	DeepSeek V3	DeepSeek	69.6	-	28.5	-	131K	$0.2002 / $0.8001	June 16, 2
41	GPT-5.1	OpenAI	68.2	73.7	76	96.3	400K	$1.25 / $10	June 16, 2
42	Gemini 3.1 Pro	Google	67.7	81.3	93	84	1M	$2 / $12	June 16, 2
43	Kimi K2.5 (Reasoning)	Moonshot AI	67.2	61.9	85	67.8	128K	$0.6 / $3	June 16, 2
44	Claude 4.1 Opus	Anthropic	64.8	38.6	56.4	77.3	200K	$15 / $75	June 16, 2
45	Mistral Large 3	Mistral	64.3	37.2	37.5	67.7	128K	$0.5 / $1.5	June 16, 2
46	Claude 4 Sonnet	Anthropic	61.1	43.6	53.4	75.5	200K	$3 / $15	June 16, 2
47	Llama 3.1 405B	Meta	58	31.2	36.5	43.8	128K	Ücretsiz	June 16, 2
48	Kimi K2.5	Moonshot AI	56.8	44.7	81	63.1	262K	$0.375 / $2.025	June 16, 2
49	Claude Haiku 4.5	Anthropic	55	44.1	53.2	73.6	200K	$1 / $5	June 16, 2
50	o4-mini (high)	OpenAI	54.3	38.5	45.5	50.3	200K	$1.1 / $4.4	June 16, 2
51	Claude 4.1 Opus Thinking	Anthropic	52.9	24.7	51.3	65.7	200K	API	June 16, 2
52	Nemotron 3 Super 100B	NVIDIA	52.5	43.3	43	40	1M	Ücretsiz	June 16, 2
53	Gemini 3 Flash	Google	52.3	44.3	47.5	72	1M	$0.5 / $3	June 16, 2
54	GPT-4o	OpenAI	52	38.6	24.4	62.2	128K	$2.5 / $10	June 16, 2
55	DeepSeek V3.2 (Thinking)	DeepSeek	51.7	61.1	51.5	59	128K	$0.55 / $2.19	June 16, 2
56	Kimi K2	Moonshot AI	51.3	30	53.4	-	128K	$0.6 / $2.5	June 16, 2
57	Claude 3.5 Sonnet	Anthropic	50.8	38.1	40.3	66.9	200K	$3 / $15	June 16, 2
58	Mistral Large 2	Mistral	47.8	32.3	32.6	41.1	128K	API	June 16, 2
59	Grok Code Fast 1	xAI	45.6	39.9	61.6	21.2	256K	$0.2 / $1.5	June 16, 2
60	Gemini 1.5 Pro	Google	45.6	33.6	14.9	65.5	2M	$1.25 / $5	June 16, 2
61	Gemini 3.1 Flash-Lite	Google	43.3	41.1	25.8	58.3	1.0M	$0.25 / $1.5	June 16, 2
62	Claude 3 Opus	Anthropic	42	33.3	13.4	58.9	200K	$15 / $75	June 16, 2
63	Qwen3 235B 2507 (Reasoning)	Alibaba	40.3	38.7	41.5	7.3	128K	Ücretsiz	June 16, 2
64	Llama 3 70B	Meta	37.2	21.9	2.6	25.8	128K	Ücretsiz	June 16, 2
65	Nemotron 3 Nano 30B	NVIDIA	37.1	19.7	16.8	12.5	32K	Ücretsiz	June 16, 2
66	MiniCPM5-1B	OpenBMB	37	-	-	-	131K	API	June 16, 2
67	DeepSeek-R1	DeepSeek	33.6	31.1	26.4	17	128K	$0.55 / $2.19	June 16, 2
68	Gemini 2.5 Flash	Google	27.3	32.9	16.5	54	1.0M	$0.3 / $2.5	June 16, 2
69	GPT-OSS 120B	OpenAI	26.3	34.3	21.4	18.9	131K	$0.039 / $0.18	June 16, 2
70	Qwen3 235B 2507	Alibaba	24.6	16.3	22.8	6.5	128K	Ücretsiz	June 16, 2
71	Llama 4 Scout	Meta	15.9	17.1	-	36.4	10M	$0.1 / $0.3	June 16, 2
72	Grok 3 [Beta]	xAI	10.9	21	28.2	9.4	128K	API	June 16, 2
73	GLM-4.5	Z.AI	7.5	22.9	7.8	5.2	131K	$0.6 / $2.2	June 16, 2
74	DeepSeek V3.1 (Reasoning)	DeepSeek	7.3	32.8	21	6.2	128K	Ücretsiz	June 16, 2
75	DeepSeek V3.1	DeepSeek	5.5	25.9	15.9	3.7	164K	$0.21 / $0.79	June 16, 2
76	Claude Mythos 5	Anthropic	-	100	100	98.9	1M	$10 / $50	June 16, 2
77	Claude Fable 5	Anthropic	-	100	100	79	1M	$10 / $50	June 16, 2
78	GLM-5.2	Z.AI	-	100	85.6	-	1.0M	$1.4 / $4.4	June 16, 2
79	Claude Opus 4.8	Anthropic	-	96	98	66.4	1M	$5 / $25	June 16, 2
80	Qwen3.7 Max	Alibaba	-	86	91.6	-	1M	$1.25 / $3.75	June 16, 2
81	Qwen3.7 Plus	Alibaba	-	84.8	87.7	76	1M	$0.32 / $1.28	June 16, 2
82	Gemini 3.5 Flash	Google	-	94.5	77.3	80	1.0M	$1.5 / $9	June 16, 2
83	DeepSeek V4 Pro (Max)	DeepSeek	-	87.1	89.7	-	1M	$1.74 / $3.48	June 16, 2
84	DeepSeek V4 Pro (High)	DeepSeek	-	81.5	86	-	1.0M	$0.435 / $0.87	June 16, 2
85	Kimi K2.6	Moonshot AI	-	82	89.8	71.3	262K	$0.68 / $3.41	June 16, 2
86	MiniMax M3	MiniMax	-	85	84.6	48.1	1.0M	$0.3 / $1.2	June 16, 2
87	DeepSeek V4 Flash (Max)	DeepSeek	-	68.4	82.2	-	1M	$0.14 / $0.28	June 16, 2
88	Qwen3.6-27B	Alibaba	-	68.7	77.9	65	262K	$0.2885 / $3.17	June 16, 2
89	Grok 4.20	xAI	-	54.2	76.4	47.6	2M	$1.25 / $2.5	June 16, 2
90	DeepSeek V4 Flash (High)	DeepSeek	-	60.1	82.5	-	1M	$0.14 / $0.28	June 16, 2
91	Nemotron 3 Ultra	NVIDIA	-	50.5	80.4	-	1M	$0.5 / $2.2	June 16, 2
92	DeepSeek V4 Pro	DeepSeek	-	65.6	68.4	-	1M	$1.74 / $3.48	June 16, 2
93	Qwen3.6 Plus	Alibaba	-	55.4	77.7	71.6	1M	$0.325 / $1.95	June 16, 2
94	Qwen3.6-35B-A3B	Alibaba	-	53.1	72.2	64	262K	$0.15 / $1	June 16, 2
95	Qwen3.5-122B-A10B	Alibaba	-	55.2	70.7	65.2	262K	$0.26 / $2.08	June 16, 2
96	Qwen3.5-27B	Alibaba	-	50.2	70.3	65.1	262K	$0.195 / $1.56	June 16, 2
97	DeepSeek V4 Flash	DeepSeek	-	47.2	62	-	1.0M	$0.09 / $0.18	June 16, 2
98	GPT-4.1	OpenAI	-	55.2	54.6	63.9	1.0M	$2 / $8	June 16, 2
99	o1	OpenAI	-	56	48.2	58.9	200K	$15 / $60	June 16, 2
100	Qwen3.5-35B-A3B	Alibaba	-	44.6	59.1	63.3	262K	$0.14 / $1	June 16, 2
101	o3-mini	OpenAI	-	61.3	49.4	65.6	200K	$1.1 / $4.4	June 16, 2
102	MiniMax M2.7	MiniMax	-	47.8	54	-	205K	$0.25 / $1	June 16, 2
103	GPT-4o mini	OpenAI	-	38.5	90.9	41.2	128K	$0.15 / $0.6	June 16, 2
104	GPT-4.1 mini	OpenAI	-	43	24.3	56.8	1.0M	$0.4 / $1.6	June 16, 2
105	DBRX Instruct	Databricks	-	8.3	60	-	32K	Ücretsiz	June 16, 2
106	o1-pro	OpenAI	-	16.1	14.5	19.3	200K	$150 / $600	June 16, 2
107	GPT-4.1 nano	OpenAI	-	22.7	8.7	37.9	1.0M	$0.1 / $0.4	June 16, 2

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

MATEMATİK LEADERBOARD

Matematik benchmark rehberi

Neden önemli?

Nasıl okunmalı?

Sınırlama