Arena

🏆 Leaderboard

As of August 20, 2026, Claude Opus 5 is #1 for Arena at 1711.88. Ranked by the Arena Code Elo score LLM Arena and Chatbot Arena Elo next to API prices. Compare human-preference ranks from Arena.ai with token cost across frontier models.

Updated August 20, 2026282 models33 providers


Claude Opus 5 Anthropic · Proprietary	1711.88	1297	—	—	1493	$30.00
Kimi K3OSS Moonshot AI · Open Source	1681.75	—	—	—	1489	$18.00
Qwen3.8 MaxOSS Qwen · Open Source	1667	1301	—	—	1491	$8.00
Grok 4.6 xAI · Proprietary	1631	—	—	—	—	$8.00
Claude Fable 5 Anthropic · Proprietary	1627	1315	1237	—	1506	$60.00
GPT-5.6 Sol OpenAI · Proprietary	1620.27	1280	—	—	1481	$35.00
GLM-5.2OSS Z AI · Open Source	1593.25	—	—	—	—	$5.80
Gemini 3.7 Flash Google · Proprietary	1587	—	—	—	1490	$4.50
Claude Opus 4.7 Anthropic · Proprietary	1558	1299	1233	—	1494	$30.00
Grok 4.5 xAI · Proprietary	1555	1285	—	—	—	$8.00
Claude Sonnet 5 Anthropic · Proprietary	1544.16	1273	1188	—	—	$12.00
Claude Opus 4.8 Anthropic · Proprietary	1539	1280	1205	—	1481	$30.00
Muse Spark 1.1 Meta · Proprietary	1538	1282	—	—	1489	$5.50
Claude Opus 4.6 Anthropic · Proprietary	1537	1293	1253	—	1497	$30.00
Muse Spark 1.2 Meta · Proprietary	1535	1290	—	—	1498	$5.50
Gemini 3.6 Flash Google · Proprietary	1527.83	1295	—	—	1484	$4.50
Claude Sonnet 4.6 Anthropic · Proprietary	1524	1275	1221	—	—	$18.00
GPT-5.6 Luna OpenAI · Proprietary	1522.94	1249	—	—	—	$1.40
Hy3OSS Tencent · Open Source	1522	—	—	—	—	$0.66
GPT-5.6 Terra OpenAI · Proprietary	1521.61	1270	—	—	—	$14.00
Qwen3.7 Max Qwen · Proprietary	1517	—	—	—	—	$5.00
GLM-5.1OSS Z AI · Open Source	1510	—	—	—	—	$5.80
Kimi K2.6OSS Moonshot AI · Open Source	1509	1263	—	—	—	$4.93
Gemini 3.5 Flash Google · Proprietary	1506.38	1284	—	—	1477	$10.50
GPT-5.5 OpenAI · Proprietary	1504.74	1286	1240	—	1482	$35.00
MiniMax M3OSS MiniMax · Open Source	1490	1240	—	—	—	$1.50
MiMo-V2.5-ProOSS Xiaomi · Open Source	1474	—	—	—	—	$1.30
Kimi K2.7 CodeOSS Moonshot AI · Open Source	1473	—	—	—	—	$4.93
Claude Opus 4.5 Anthropic · Proprietary	1468	—	1179	—	—	$30.00
Qwen3.6 Plus Qwen · Proprietary	1460	—	—	—	—	$3.50
Gemini 3.5 Flash-Lite Google · Proprietary	1449	1260	—	—	—	$2.80
Gemini 3.1 Pro Google · Proprietary	1447	1277	1212	—	1486	$17.50
DeepSeek-V4-Pro-0813OSS DeepSeek · Open Source	1446	—	—	—	—	$5.28
MiMo-V2.5OSS Xiaomi · Open Source	1438	1238	—	—	—	$0.50
Gemini 3 Pro Google · Proprietary	1438	1289	1207	—	1485	$14.00
Gemini 3 Flash Google · Proprietary	1438	1271	1197	—	—	$3.50
GLM-5OSS Z AI · Open Source	1436	—	—	—	—	$4.20
GLM-4.7OSS Z AI · Open Source	1434	—	—	—	—	$2.80
Kimi K2.5OSS Moonshot AI · Open Source	1430.56	—	—	—	—	$3.68
GPT-5 Medium OpenAI · Proprietary	1419	—	—	—	—	$11.25
GPT-5.2 OpenAI · Proprietary	1418	1244	1206	—	—	$15.75
GPT-5.3 Codex OpenAI · Proprietary	1406.65	—	—	—	—	$15.75
GPT-5.4 mini OpenAI · Proprietary	1402.17	1253	—	—	—	$5.25
Qwen3.5-397B-A17BOSS Qwen · Open Source	1400	1247	—	—	—	$4.20
GLM-5V-TurboOSS Z AI · Open Source	1400	—	—	—	—	$5.20
MiniMax M2.7OSS MiniMax · Open Source	1397	—	—	—	—	$1.50
GPT-5 OpenAI · Proprietary	1395	—	1132	—	—	$11.25
MiniMax M2.1OSS MiniMax · Open Source	1391.64	—	—	—	—	$1.50
GPT-5.1 Medium OpenAI · Proprietary	1391	—	—	—	—	$11.25
GPT-5.4 OpenAI · Proprietary	1390	1280	1196	—	—	$17.50

Showing 1–50 of 282 models

Next step

You found the model. Now ship the product.

Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.

Get the stack — $249 Have us build it with you

The index

All Large Language Models

282 models across 33 providers. Search or jump to a lab — every model page stays linked here.

Cursor

2 models

Composer 2 Composer 2 Fast

xAI

15 models

Grok 4.6 Grok 4.5 Grok 4.3 Grok-4.1 Grok-4.1 Fast Non-Reasoning Grok-4.1 Fast Reasoning Grok-4.1 Thinking Grok 4 Fast Grok Code Fast 1 Grok-4 Fast Non-Reasoning Grok-4 Fast Reasoning Grok-4 Grok-3 Grok-3 Mini Grok-2

DeepSeek

16 models

DeepSeek-V4-Pro-0813 DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0423 DeepSeek-V4-Flash-Max DeepSeek-V4-Pro-Max DeepSeek-V3.2 DeepSeek-V3.2 (Non-thinking)DeepSeek-V3.2-Exp DeepSeek-R1-0528 DeepSeek-V3 0324 DeepSeek R1 Distill Llama 70B DeepSeek R1 Distill Qwen 32B DeepSeek-R1 DeepSeek-V3.1 DeepSeek-V3 DeepSeek-V2.5

MiniMax

6 models

MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiniMax M2.1 MiniMax M2 MiniMax M1 80K

AI21 Labs

2 models

Jamba 1.5 Large Jamba 1.5 Mini

Amazon

5 models

Nova 2 Lite Nova 2 Sonic Nova Lite Nova Micro Nova Pro

Baidu

1 models

ERNIE 4.5

ByteDance

2 models

Seed 2.1 Turbo Seed 2.0 Pro

Cohere

3 models

North Mini Code 1.0 Command A+Command R+

IBM

1 models

Granite 3.3 8B Instruct

Inception

1 models

Mercury 2

inclusionAI

1 models

Ling-3.0-flash

LG AI Research

1 models

K-EXAONE-236B-A23B

Meituan

4 models

LongCat-Flash-Lite LongCat-Flash-Thinking-2601 LongCat-Flash-Thinking LongCat-Flash-Chat

Microsoft

5 models

MAI-Code-1.1-Flash Phi 4 Mini Phi-4-multimodal-instruct Phi 4 Phi-3.5-mini-instruct

Moonshot AI

9 models

Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 Kimi K2 0905 Kimi K2-Instruct-0905 Kimi K2-Thinking-0905 Kimi K2 Instruct

Nous Research

1 models

Hermes 3 70B

NVIDIA

5 models

Nemotron 3.5 Lightning (30B A3B)Nemotron 3 Ultra (550B A55B)Nemotron 3 Super (120B A12B)Nemotron 3 Nano (30B A3B)Nemotron Nano 9B v2

Poolside

2 models

Laguna S 2.1 Laguna XS 2.1

Sakana AI

1 models

Sakana Namazu

StepFun

1 models

Step-3.5-Flash

Tencent

1 models

Hy3

Thinking Machines

1 models

Inkling-Small

Unisound

1 models

Upstage

1 models

Solar Pro 4

Xiaomi

3 models

MiMo-V2.5-Pro MiMo-V2.5 MiMo-V2-Flash

Which model leads Arena right now?

As of August 20, 2026, Claude Opus 5 by Anthropic is #1 for Arena at 1711.88. Ranked by the Arena Code Elo score This board also tracks Arena Code Elo, Arena Vision Elo, Arena Search Elo, Arena-Hard. Next on the same board: Kimi K3 and Qwen3.8 Max. Related leaders: Claude Fable 5 on Arena Vision Elo at 1315; Claude Opus 4.6 on Arena Search Elo at 1253. This arena leaderboard ranks models by Arena Code Elo. Scores come from public evals. Prices are the live API rates in the table above.

Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)

Top 8 for arena. Ranked by the Arena Code Elo score Input and output are dollars per million tokens.
Rank	Model	Arena Code Elo	Input /M	Output /M
1	Claude Opus 5	1711.88	$5.00	$25.00
2	Kimi K3	1681.75	$3.00	$15.00
3	Qwen3.8 Max	1667	$2.00	$6.00
4	Grok 4.6	1631	$2.00	$6.00
5	Claude Fable 5	1627	$10.00	$50.00
6	GPT-5.6 Sol	1620.27	$5.00	$30.00
7	GLM-5.2	1593.25	$1.40	$4.40
8	Gemini 3.7 Flash	1587	$0.75	$3.75

Related LLM leaderboards

LLM Leaderboard Coding Math Agentic Reasoning Writing Science Finance Long Context Vision Open Source

Individual benchmark pages

Rank one eval at a time. All LLM benchmarks.

HLE SWE Bench Humanity's Last Exam (No Tools)Humanity's Last Exam (With Tools)Terminal-Bench 2.0 Terminal-Bench Terminal-Bench 2.1 Terminal-Bench 2 Terminal-Bench 3.0 ARC-AGI-1 Verified

Arena FAQ

Who ranks #1 on the Arena leaderboard?

As of August 20, 2026, Claude Opus 5 by Anthropic ranks #1 on Arena Code Elo at 1711.88. API pricing is $5.00/M input and $25.00/M output.

What are the top models on Arena Code Elo?

The current Arena Code Elo ranking as of August 20, 2026 is 1. Claude Opus 5 at 1711.88; 2. Kimi K3 at 1681.75; 3. Qwen3.8 Max at 1667.

Which arena model is the cheapest?

MiMo-V2-Flash is the cheapest scored model on this arena leaderboard at $0.10/M input and $0.30/M output ($0.40 blended). Claude Opus 5 still leads Arena Code Elo at 1711.88.

Should I always pick the #1 Arena Code Elo model?

Not automatically. Claude Opus 5 leads Arena Code Elo, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh Arena Code Elo against input/output price, context window, and related evals.

How often is the Arena leaderboard updated?

Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 20, 2026. Treat it as a current index, not a one-off blog post.

What is LLM Arena?

LLM Arena, also called Chatbot Arena or LMSYS Arena, ranks models from blind human votes. Elo is a preference score, not a homework-test score.

How is Arena Elo different from SWE-bench?

Arena Elo is human preference in chat. SWE-bench is automated GitHub issue fixing. A model can win Arena and still lose coding evals.

Do you replace lmarena.ai?

No. Use Arena.ai for the official vote graph. This page puts the Elo we have next to live API prices so you can budget a preferred model.

You found the model. Now ship the product.

All Large Language Models

OpenAI

Anthropic

Google

Cursor

xAI

DeepSeek

MiniMax

Qwen

AI21 Labs

Amazon

Baidu

ByteDance

Cohere

IBM

Inception

inclusionAI

LG AI Research

Meituan

Meta

Microsoft

Mistral

Moonshot AI

Nous Research

NVIDIA

Poolside

Sakana AI

StepFun

Tencent

Thinking Machines

Unisound

Upstage

Xiaomi

Z AI

Which model leads Arena right now?

Related LLM leaderboards

Individual benchmark pages

Arena FAQ

Who ranks #1 on the Arena leaderboard?

What are the top models on Arena Code Elo?

Which arena model is the cheapest?

Should I always pick the #1 Arena Code Elo model?

How often is the Arena leaderboard updated?

What is LLM Arena?

How is Arena Elo different from SWE-bench?

Do you replace lmarena.ai?