📜 Peringkat: Konteks panjang

Pencarian dan penalaran pada input sangat panjang: MRCR v2 dan ukuran jendela.

🏆 Keseluruhan673 💻 Coding392 📐 Matematika32 🧠 Penalaran391 🤖 Agen31 📚 Pengetahuan388 👁️ Multimodal370 🛠️ Agen coding40 🔬 Penalaran ilmiah45 🌍 Multibahasa12 ✍️ Menulis53 💬 Chat & asisten53 🔭 Riset48 🔧 Pemanggilan alat31 📜 Konteks panjang55 ⚡ Kecepatan378 💰 Nilai377 🔓 Bobot terbuka153

Model: 55

#	Model	Podium Score	MRCR v2	Kecepatan
01	GPT-5.6 Sol OpenAI	100.0	91.5%	72 t/s
02	GPT-5.4 OpenAI	100.0	—	60 t/s
03	Claude Fable 5 Anthropic	99.2	—	71 t/s
4	Kimi K3 Moonshot AI · Terbuka	99.2	—	37 t/s
5	Claude Opus 5 Anthropic	99.2	—	60 t/s
6	Qwen3.8 Max Alibaba	99.2	—	55 t/s
7	Claude Opus 4.8 Anthropic	99.2	—	50 t/s
8	Muse Spark 1.1 Meta	99.2	—	208 t/s
9	Gemini 3.6 Flash Google	99.2	—	233 t/s
10	Claude Opus 4.7 Anthropic	99.2	—	80 t/s
11	Qwen3.7 Max Alibaba	99.2	—	203 t/s
12	Gemini 3.5 Flash Google	99.2	—	267 t/s
13	MiMo V2.5 Pro Xiaomi · Terbuka	99.2	—	65 t/s
14	DeepSeek V4 Pro DeepSeek · Terbuka	99.2	—	66 t/s
15	Claude Sonnet 5 Anthropic	99.2	—	96 t/s
16	Qwen3.7 Plus Alibaba	99.2	—	54 t/s
17	DeepSeek V4 Flash DeepSeek · Terbuka	99.2	—	113 t/s
18	Gemini 3.5 Flash-Lite Google	99.2	—	389 t/s
19	Claude Sonnet 4.6 Anthropic	99.2	—	50 t/s
20	Qwen3.6 Plus Alibaba	99.2	—	55 t/s
21	GPT-5.6 Terra OpenAI	98.4	89.6%	127 t/s
22	Inkling Small Thinking Machines	93.6	—	130 t/s
23	MiniMax M3 MiniMax	93.6	—	93 t/s
24	Inkling Thinking Machines	93.6	—	81 t/s
25	Nemotron 3 Ultra 550B NVIDIA · Terbuka	93.4	—	142 t/s
26	Grok 4.5 xAI	93.2	—	59 t/s
27	Grok 4.3 xAI	93.2	—	129 t/s
28	GPT-5.3 Codex OpenAI	91.2	—	118 t/s
29	GPT-5.1 OpenAI	91.2	—	60 t/s
30	GPT-5 OpenAI	91.2	—	60 t/s
31	GLM-5.2 Z.ai · Terbuka	87.5	—	164 t/s
32	Kimi K2.6 Moonshot AI · Terbuka	87.5	—	40 t/s
33	Nex N2 Pro Nex AGI	87.5	—	138 t/s
34	Kimi K2.7 Code Moonshot AI · Terbuka	87.5	—	39 t/s
35	Hunyuan Hy3 Tencent	87.5	—	69 t/s
36	Gemma 4 31B Google · Terbuka	87.5	—	35 t/s
37	Qwen3.5 397B-A17B Alibaba · Terbuka	87.5	—	71 t/s
38	Qwen3.5 122B-A10B Alibaba · Terbuka	87.5	—	126 t/s
39	Qwen3 Max Alibaba · Terbuka	87.5	—	85 t/s
40	Claude Opus 4.6 Anthropic	86.3	76%	50 t/s
41	Claude Opus 4.5 Anthropic	85.2	—	50 t/s
42	Claude Sonnet 4.5 Anthropic	85.2	—	80 t/s
43	o3 OpenAI	85.2	—	90 t/s
44	Claude Opus 4.1 Anthropic	85.2	—	80 t/s
45	GPT-5.5 OpenAI	84.9	74%	60 t/s
46	DeepSeek V3.2 DeepSeek · Terbuka	83.5	—	60 t/s
47	DeepSeek R1 DeepSeek · Terbuka	83.5	—	60 t/s
48	GPT-5.2 OpenAI	81.3	—	90 t/s
49	GPT-5.6 Luna OpenAI	56.6	41.3%	175 t/s
50	Gemini 3.1 Pro Google	43.3	26.3%	136 t/s
51	Gemini 3 Pro Google	43.3	26.3%	120 t/s
52	Gemini 3 Flash Google	39.7	22.1%	120 t/s
53	Seed 2.0 Pro ByteDance	13.8	—	40 t/s
54	ERNIE 5.1 Baidu	11.0	—	60 t/s
55	Muse Spark Meta	0.0	—	80 t/s

Podium Score adalah campuran berbobot dari lima papan peringkat. Selengkapnya di metodologi.