Best LLMs — 2026 Rankings

LLM Leaderboard

The definitive ranking of every major LLM — open and closed source — compared across reasoning, coding, math, agentic, software engineering, and chat benchmarks.

Orchexa Team · Last updated: 2026-05-17

Claude Mythos PreviewN/AGPT-5.5N/AClaude Opus 4.7N/AClaude Opus 4.6N/AGPT-5.4N/A

GPT-5.2 ProN/AGemini 3 ProN/AGemini 3.1 ProN/AClaude Sonnet 4.6N/AGrok 4.20N/A

Gemini 3 FlashN/AGPT-oss 120B117BNemotron Ultra 253B253BMuse SparkN/ASeed 2.0 ProN/A

Mercury 2N/AGrok 3N/ADeepSeek V3671BLlama 4 Maverick400B

Benchmarks Scores Head to Head

Best LLMs by Task — Benchmark Rankings

Which LLM is best for coding, reasoning, or agentic tasks? See how every model stacks up across key benchmarks.

Best Overall (MMLU)

Best Multilingual

Best Visual Reasoning

Hardest Exam

LLM Benchmark Scores & Pricing

Complete benchmark results and pricing for every major LLM. Click any column header to sort and rank.

Filter:

Model ↕	Params ↕	Context ↕	Input $/1M ↕	Output $/1M ↕	MMLU-Pro ↓	GPQA Diamond ↕	IFEval ↕	Chatbot Arena ↕	SWE-bench Verified ↕	HumanEval ↕	LiveCodeBench ↕	AIME 2025 ↕	MATH-500 ↕	MMLU ↕	MMMLU ↕	MMMU-Pro ↕	HLE ↕	Terminal-Bench 2.0 ↕	ARC-AGI-2 ↕	τ2-bench ↕	OSWorld ↕	BrowseComp ↕
GPT-oss 120BOpenAI	117B	128K	N/A	N/A	90	80.9	N/A	1355	62.4	88.3	60	97.9	N/A	90	N/A	N/A	N/A	18.7	N/A	N/A	N/A	N/A
GPT-5.5OpenAI	N/A	1.1M	$7.78	$24.00	88.4	93.6	92	1505	82.1	96	83	100	97	92	N/A	83.4	56.7	77.2	61.5	88.5	78	85.3
Kimi K2.6Moonshot	1T	262K	$0.50	$1.29	88.4	90.5	94.8	1465	79.6	99.2	87	97.5	98.4	92.5	N/A	80	54.5	54.3	N/A	N/A	N/A	N/A
Qwen 3.5Qwen	397B	262K	N/A	N/A	87.8	88.4	92.6	1450	76.4	N/A	83.6	N/A	N/A	88.5	88.5	79	28.7	52.5	N/A	86.7	62.2	78.6
DeepSeek V4 Pro MaxDeepSeek	685B	1M	$0.50	$1.93	87.2	88.7	92	1442	76.5	94.5	81.4	94.5	97.5	91	N/A	76	40.5	51.2	N/A	N/A	N/A	N/A
Kimi K2.5Moonshot	1T	262K	N/A	N/A	87.1	87.6	94	1438	76.8	99	85	96.1	98	92	N/A	78.5	N/A	50.8	N/A	N/A	N/A	N/A
Claude Mythos PreviewAnthropic	N/A	200K	$20.00	$100.00	86.5	94.6	95.4	1521	83.2	97	83.5	100	98.5	92.5	92.8	79.6	58.2	70.8	71.3	93.4	76.1	87.5
Qwen3.6 PlusQwen	480B	1M	$0.39	$0.78	86.4	89.5	92.8	1458	78	96	84.2	96.5	N/A	89.5	89.5	80.5	31.5	54	N/A	87.5	64.8	80.1
GPT-5.2 ProOpenAI	N/A	400K	$5.00	$20.00	86.1	91.5	N/A	1481	75	92.5	78	98.5	96	90.5	N/A	80	52.5	68	N/A	N/A	N/A	N/A
Step-3.5-FlashStepfun	196B	262K	$0.10	$0.30	85.8	N/A	N/A	N/A	74.4	81.1	86.4	99.8	N/A	N/A	N/A	N/A	N/A	51	N/A	N/A	N/A	N/A
Gemini 3.1 ProGoogle	N/A	1M	$2.00	$12.00	85	91.9	85	1492	78	93	81.3	100	94	91.8	91.8	81	45.8	56.2	31.1	85.3	N/A	59.2
DeepSeek V3.2DeepSeek	685B	130K	$0.28	$0.42	85	79.9	N/A	1423	67.8	N/A	74.1	89.3	N/A	88.5	N/A	N/A	N/A	39.6	N/A	N/A	N/A	N/A
MiMo-V2-FlashXiaomi	309B	262K	N/A	N/A	84.9	83.7	N/A	N/A	73.4	84.8	80.6	94.1	N/A	86.7	N/A	N/A	N/A	38.5	N/A	N/A	N/A	N/A
DeepSeek R1DeepSeek	671B	128K	$0.28	$0.42	84	71.5	83.3	1398	49.2	90.2	65.9	87.5	97.3	90.8	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
Claude Opus 4.7Anthropic	N/A	200K	$15.00	$75.00	83.8	92.4	94.5	1510	82.5	95.5	78.6	100	98	91.5	91.5	78.8	55	67.9	69.5	92.5	74.3	85
Gemini 3 ProGoogle	N/A	1M	$2.00	$12.00	83.5	89.2	86.5	1479	72.4	91	76.8	96	93	90	90	78.4	42.3	50	N/A	83.5	N/A	56.5
Claude Opus 4.6Anthropic	N/A	200K	$15.00	$75.00	82	91.3	94	1503	80.8	95	76	100	97.6	91	91.1	77.3	53	65.4	68.8	91.9	72.7	84
Muse SparkMeta	N/A	1M	N/A	N/A	81.7	78.5	N/A	1372	58	84.5	63	82	N/A	87	86.5	N/A	N/A	38.6	N/A	N/A	N/A	N/A
DeepSeek V3DeepSeek	671B	128K	$0.28	$1.10	81.2	68.4	N/A	1359	38.8	N/A	49.2	N/A	94	88.5	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
Seed 2.0 ProByteDance	N/A	200K	N/A	N/A	80.5	83.1	88.5	1382	61	85.5	67	85	91	86	N/A	68.5	N/A	41.8	N/A	N/A	N/A	N/A
Llama 4 MaverickMeta	400B	1M	N/A	N/A	80.5	69.8	N/A	1328	N/A	62	43.4	N/A	N/A	85.5	84.6	N/A	N/A	N/A	N/A	N/A	N/A	N/A
Claude Sonnet 4.6Anthropic	N/A	200K	$3.00	$15.00	79.1	89.9	N/A	1460	79.6	92.1	72.4	52.8	97.8	N/A	89.3	75.6	49	59.1	58.3	91.7	72.5	74.7
Gemini 3 FlashGoogle	N/A	1M	$0.15	$0.78	78.6	80.4	83.5	1432	65	88	68.5	91	91.5	86.5	N/A	70.2	N/A	43.5	N/A	N/A	N/A	N/A
MiniMax M2.5MiniMax	230B	205K	$0.30	$1.20	76.5	85.2	87.5	1404	80.2	89.6	65	86.3	N/A	85	N/A	N/A	N/A	42.2	N/A	N/A	N/A	N/A
Mercury 2Inception	N/A	131K	$0.25	$1.00	75.5	72	N/A	1345	N/A	83	56	78	N/A	83	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
GLM-5Zhipu AI	744B	200K	N/A	N/A	70.4	86	88	1454	77.8	90	52	84	88	85	N/A	50.4	N/A	56.2	N/A	89.7	N/A	75.9
Grok 4.20xAI	N/A	2M	$4.00	$18.00	N/A	89.4	85	1454	68.5	96	82.5	96.5	N/A	N/A	N/A	N/A	N/A	63.5	N/A	N/A	N/A	78.2
GPT-5.4OpenAI	N/A	1M	$2.50	$15.00	N/A	92.8	N/A	1463	N/A	N/A	N/A	N/A	N/A	N/A	N/A	81.2	N/A	75.1	N/A	N/A	75	82.7
Mistral LargeMistral	675B	256K	N/A	N/A	N/A	43.9	N/A	1416	N/A	92	82.8	88	93.6	85.5	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
Nemotron Ultra 253BNvidia	253B	128K	N/A	N/A	N/A	76	89.5	1348	N/A	N/A	66.3	72.5	97	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A
Grok 3xAI	N/A	131K	$3.00	$15.00	N/A	84.6	N/A	1412	49	94.5	79.4	93.3	N/A	N/A	N/A	N/A	N/A	52	N/A	N/A	N/A	N/A

Compare LLMs Head-to-Head

Select two models to see how they stack up across all benchmarks.

Model A

Model B

GPT-5.5Claude Mythos Preview

MMLU-Pro

88.4

86.5

GPQA Diamond

93.6

94.6

IFEval

95.4

Chatbot Arena

1505

1521

SWE-bench Verified

82.1

83.2

HumanEval

LiveCodeBench

83.5

AIME 2025

100

MATH-500

98.5

MMLU

92.5

MMMU-Pro

83.4

79.6

HLE

56.7

58.2

Terminal-Bench 2.0

77.2

70.8

ARC-AGI-2

61.5

71.3

τ2-bench

88.5

93.4

OSWorld

76.1

BrowseComp

85.3

87.5

Benchmarks won

4vs12

Deploy AI Agentsthat drive real revenue

Dùng thử miễn phí Tìm hiểu giải pháp Doanh nghiệp