Leaderboard
LLM Leaderboard & Arena Rankings 2026.
Complete LLM leaderboard with daily-updated benchmark scores. Compare and rank the best LLMs by GPQA, MMLU, HLE, SWE-bench, and more alongside API pricing.
 Gemini 3 Pro Preview Google | 45.8% | 91.9% | 91.9% | 76.2% | 72.1% | 100% | — | — | — | — |
 gpt-5.4-pro OpenAI | — | — | 90.5% | — | — | — | — | — | — | — |
gpt-5.4 OpenAI | 39.8% | 92.8% | 89.4% | — | — | — | — | — | — | — |
gpt-5.1 OpenAI | — | 88.1% | 88.1% | 76.3% | — | 94% | — | — | — | — |
gpt-5.2-pro OpenAI | 36.6% | 93.2% | 87.9% | — | — | 100% | — | 74.1% | — | — |
gpt-5.3-codex OpenAI | — | — | 87.7% | — | — | — | — | — | — | — |
 Grok 4 xAI | 40% | 87.5% | 87.5% | — | — | 91.7% | — | — | — | — |
gpt-5 OpenAI | 24.8% | 85.7% | 87.3% | 74.9% | — | 94.6% | — | — | — | — |
 Claude Opus 4.5 Anthropic | — | 87% | 87% | 80.9% | — | — | — | 90.8% | — | — |
Gemini 2.5 Pro Google | 17.8% | 83% | 86.4% | 63.2% | 50.8% | 83% | — | 88.9% | 90.9% | 88.2% |
gpt-5.2 OpenAI | 34.5% | 92.4% | 85.4% | 80% | — | 100% | — | 88% | — | — |
Grok 3 xAI | — | 84.6% | 84.6% | — | — | 93.3% | — | 79.9% | — | — |
 Kimi K2 Thinking Moonshot AI | — | — | 84.5% | — | — | 99.1% | — | — | — | — |
Claude Sonnet 4.5 Anthropic | — | 83.4% | 83.4% | — | — | 87% | — | — | — | — |
o3 OpenAI | 14.7% | 83.3% | 83.3% | 69.1% | — | 98.4% | — | 93.4% | — | — |
o4-mini OpenAI | 14.7% | 81.4% | 81.4% | 68.1% | — | 92.7% | — | — | — | — |
o3-mini OpenAI | — | 77.2% | 79.7% | 49.3% | 15% | — | 97.9% | — | — | — |
Claude Opus 4 Anthropic | — | 79.6% | 79.6% | 72.5% | — | 75.5% | — | 88.8% | — | — |
Gemini 2.5 Flash Google | 11% | 82.8% | 78.3% | 60.4% | 26.9% | 72% | — | — | 50.4% | — |
o1 OpenAI | — | 78% | 75.7% | 41% | 47% | — | 96.4% | — | — | — |
Claude Sonnet 4 Anthropic | — | 75.4% | 75.4% | 72.7% | — | 70.5% | — | 84% | 91.4% | 88.7% |
Claude Haiku 4.5 Anthropic | — | 73% | 73% | 73.3% | — | 80.7% | — | 90.8% | — | 85.2% |
 DeepSeek R1OSS DeepSeek | — | — | 71.5% | — | — | — | 97.3% | — | — | — |
gpt-4.5-preview OpenAI | — | — | 71.4% | — | — | — | — | — | — | — |
 Llama 4 MaverickOSS Meta | — | 69.8% | 69.8% | — | — | — | — | — | — | — |
Claude Sonnet 3.7 Anthropic | — | 84.8% | 68% | 70.3% | — | 54.8% | 82.2% | — | — | — |
gpt-4.1-mini OpenAI | 3.7% | 65% | 65% | 23.6% | — | 40.2% | — | 80.1% | 9.8% | 54.6% |
Claude 3.5 Sonnet Anthropic | — | 67.2% | 65% | 49% | — | — | 78% | 90.4% | 95.4% | 96.4% |
DeepSeek V3OSS DeepSeek | — | 59.1% | 64.8% | 42% | 24.9% | — | 94% | — | — | — |
Gemini 2.0 Flash Google | — | 62.1% | 62.1% | — | — | — | 89.7% | — | — | — |
o1 mini OpenAI | — | 60% | 60% | — | — | — | 90% | 85.2% | — | 92.4% |
Llama 4 ScoutOSS Meta | — | 57.2% | 57.2% | — | — | — | — | 79.6% | — | — |
GPT-4o OpenAI | 5.3% | 70.1% | 56.1% | 33.2% | 38.2% | — | 60.3% | 88.7% | 95% | 90% |
Llama 3.3 70B Meta | — | — | 50.5% | — | — | — | 77% | 86% | 86.5% | 88.4% |
gpt-4.1-nano OpenAI | — | 50.3% | 50.3% | — | — | — | — | 80.1% | — | 54.6% |
Llama 3.1 405B Meta | — | — | 49% | — | — | — | 73.8% | 87% | — | 89% |
 Amazon Nova Pro Amazon | — | — | 46.9% | — | — | — | 76.6% | 85.9% | — | — |
gpt-4.1 OpenAI | 5.4% | 66.3% | 43.4% | 54.6% | — | 46.4% | — | — | — | 67% |
Claude 3.5 Haiku Anthropic | — | 41.6% | 41.6% | 40.6% | — | — | 69.4% | — | — | — |
GPT-4o-mini OpenAI | — | 40.2% | 40.2% | 8.7% | — | — | 70.2% | 82% | — | 87.2% |
Amazon Nova 2 Lite Amazon | — | — | — | — | — | — | — | — | — | — |
Amazon Nova 2 Omni Amazon | — | — | — | — | — | — | — | — | — | — |
Amazon Nova 2 Pro Amazon | — | — | — | — | — | — | — | — | — | — |
Amazon Nova Lite Amazon | — | — | — | — | — | — | — | 75% | — | — |
Amazon Nova Micro Amazon | — | — | — | — | — | — | — | — | — | — |
Amazon Nova Premier Amazon | — | — | — | — | — | — | — | 87.4% | — | — |
Claude 2 Anthropic | — | — | — | — | — | — | — | 78.5% | 92.3% | 94.5% |
Claude 2.1 Anthropic | — | — | — | — | — | — | — | 78.5% | 91% | 87.5% |
Claude 3 Haiku Anthropic | — | 33.3% | — | — | — | — | — | 76.7% | 85.9% | — |
Claude 3 Opus Anthropic | — | 50.4% | — | — | — | — | — | 88.2% | 95.4% | 73% |
Showing 1–50 of 336 models
Building with these APIs?
Get 10+ Next.js AI templates with auth, payments, and more.
All Large Language Models
OpenAI
60 modelsgpt-5.4·gpt-5.4-pro·gpt-5.3-chat-latest·gpt-5.3-instant·gpt-5.3-codex·GPT-5.2 Codex·gpt-5.2·gpt-5.1-codex·gpt-5.1-codex-mini·GPT-5.1 Codex High·GPT-5.1 High·GPT-5.1 Instant·GPT-5.1 Medium·GPT-5.1 Thinking·gpt-5-codex·gpt-5.2-pro·gpt-5·GPT-5 High·GPT-5 Medium·gpt-5-mini·gpt-5-nano·GPT OSS 120B·GPT OSS 120B High·GPT OSS 20B·GPT OSS 20B High·o3-pro·o3·o4-mini·gpt-4.1·gpt-4.1-mini·gpt-4.1-nano·o1-pro·gpt-4.5-preview·o3-mini·o1·gpt-5-pro·gpt-5.1·o1 mini·o1 preview·o1-mini-2024-09-12·o1-preview-2024-09-12·GPT-4o-2024-08-06·GPT-4o-mini·GPT-4o·GPT-4o-2024-05-13·GPT-4-turbo-2024-04-09·GPT-3.5-turbo-0125·GPT-4-turbo-0125·GPT-3.5-turbo-1106·GPT-4 Turbo·GPT-4-turbo-1106·computer-use-preview·gpt-4o-audio-preview·GPT-3.5-turbo-16k·GPT-4-0613·GPT-4-32k-0613·GPT-3.5 Turbo·GPT-4·GPT-4-32k·GPT-3.5-turbo
Anthropic
21 modelsClaude Sonnet 4.6·Claude Opus 4.6·Claude Opus 4.5·Claude Haiku 4.5·Claude Sonnet 4.5·Claude Opus 4.1·Claude Opus 4·Claude Sonnet 4·Claude Sonnet 3.7·Claude Haiku 3.5·Claude 3.5 Haiku·Claude 3.5 Sonnet·Claude 3 Haiku·Claude Haiku 3·Claude 3 Opus·Claude 3 Sonnet·Claude Opus 3·Claude 2.1·Claude Instant 1.2·Claude 2·Claude Sonnet 3.5
Gemini 3.1 Flash Lite Preview·Gemini 3.1 Pro·Gemini 3 Flash Preview·Gemini 3 Pro Preview·Gemma 3n E4B Instructed·Gemini 2.5 Flash Lite·Gemini 2.5 Pro·Gemini 2.5 Pro Preview 06-05·Gemini 2.5 Flash·Gemma 3 12B·Gemma 3 27B·Gemma 3 4B·Gemini 2.0 Flash·Gemini 2.0 Flash Lite·Gemini 1.5 Pro·Gemini 1.5 Flash·Gemini 1.5 Flash·Gemini 1.5 Flash 8B·Gemini 1.0 Pro·Gemini 1.5 Pro
Perplexity
5 modelsxAI
16 modelsDeepSeek
13 models
Groq
9 models
MiniMax
4 models
Qwen
29 modelsQwen 3.5 397B A17B·Qwen3 Max·Qwen3 VL 235B A22B Instruct·Qwen3 VL 235B A22B Thinking·Qwen3 VL 30B A3B Instruct·Qwen3 VL 30B A3B Thinking·Qwen3 VL 4B Instruct·Qwen3 VL 4B Thinking·Qwen3 VL 8B Instruct·Qwen3 VL 8B Thinking·Qwen3-Next-80B-A3B-Instruct·Qwen3-Next-80B-A3B-Thinking·Qwen Plus Latest·Qwen3-235B-A22B-Thinking-2507·Qwen3-235B-A22B-Instruct-2507·Qwen 3 14B·Qwen 3 235B A22B·Qwen 3 30B A3B·Qwen 3 32B·Qwen 3 8B·Qwen3-Coder·QwQ-32B-Preview·Qwen 2.5 72B Instruct·Qwen2.5 7B Instruct·Qwen2.5-Coder 32B Instruct·Qwen 3 4B·Qwen Max Latest·Qwen QwQ Plus·Qwen Turbo Latest
01.ai
1 models
AI21 Labs
2 modelsAmazon
10 models
Anyscale
2 modelsBaidu
1 models
Cerebras
5 models
Cohere
4 models
DeepInfra
6 models
Fireworks
10 models
Hyperbolic
4 models
IBM
1 modelsIBM Watsonx
6 modelsInception
1 modelsLG AI Research
1 modelsMeituan
4 modelsMeta
13 modelsMicrosoft
3 models
Mistral
32 modelsMin istral 3 (3B Reasoning 2512)·Ministral 3 (14B Reasoning 2512)·Ministral 3 (8B Reasoning 2512)·Mistral Large 3 (675B Instruct 2512)·Mistral Large 3·Codestral·Devstral Small 1.1·Devstral Medium·Magistral Medium·Mistral Small 3.1·Mistral Small 3.1 24B Base·Mistral Small 3 24B Instruct·Mistral Large 2411·Pixtral Large 2411·Pixtral Large·Ministral 8B Instruct·Mistral Small·Pixtral-12B·Mistral Large 2·Mistral NeMo Instruct·Mistral Large·Mistral 7B Instruct·Magistral Small·Mistral Codestral·Mistral Devstral·Mistral Devstral 2·Mistral Devstral Small 2·Mistral Medium 3·Mistral Ministral 3B·Mistral Ministral 8B·Mistral Nemo·Mistral Nemo 2407
Moonshot AI
5 models
Nebius AI Studio
5 modelsNous Research
1 modelsNVIDIA
1 models
Reka
3 models
Replicate
5 models
SambaNova Cloud
5 modelsStepFun
1 models
Together.AI
10 models
Writer
8 modelsXiaomi
1 models