Easy Benchmarks
Workspace
Overview
Benchmarks
Benchmarks list
Compare
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
LLMs
Audio
Image
Video
Feedback
Log inSign up
Back

Overall

General leaderboard using the Artificial Analysis Intelligence Index.

Leader

Domain score averages relative percentile across included metrics.

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

Domain score 100

Overall

Top Overall Models

General leaderboard using the Artificial Analysis Intelligence Index.

Domain Leaderboard

RankModelCreatorDomain ScoreSpeedBlended Price
#1Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic100.066.3 tok/s$10.94/M
#2GPT-5.5 (xhigh)OpenAI99.862.4 tok/s$11.25/M
#3
GPT-5.5 (high)
OpenAI
99.6
62.3 tok/s
$11.25/M
#4Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic99.461.8 tok/s$10.94/M
#5Gemini 3.1 Pro PreviewGoogle99.2135.9 tok/s$4.50/M
#6GPT-5.4 (xhigh)OpenAI99.075.5 tok/s$5.63/M
#7GPT-5.5 (medium)OpenAI98.959.2 tok/s$11.25/M
#8Qwen3.7 MaxAlibaba98.7186.5 tok/s$3.75/M
#9Gemini 3.5 Flash (high)Google98.5212.4 tok/s$3.38/M
#10Gemini 3.5 Flash (medium)Google98.3210.2 tok/s$3.38/M
#11MiniMax-M3MiniMax98.145.6 tok/s$0.525/M
#12Kimi K2.6Kimi97.941.6 tok/s$1.71/M
#13MiMo-V2.5-ProXiaomi97.743.3 tok/s$0.544/M
#14GPT-5.3 Codex (xhigh)OpenAI97.598.6 tok/s$4.81/M
#15Qwen3.7 PlusAlibaba97.353.6 tok/s$0.590/M
#16Grok 4.3 (high)xAI97.1237.5 tok/s$1.56/M
#17Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic96.947.3 tok/s$10.94/M
#18Muse SparkMeta96.7n/a-
#19Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic96.648.1 tok/s$10.94/M
#20Qwen3.6 Max PreviewAlibaba96.440.9 tok/s$2.93/M
#21Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic96.270.4 tok/s$6.56/M
#22DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek96.061.8 tok/s$0.544/M
#23GLM-5.1 (Reasoning)Z AI95.846.8 tok/s$2.15/M
#24GPT-5.2 (xhigh)OpenAI95.671 tok/s$4.81/M
#25GPT-5.5 (low)OpenAI95.460.2 tok/s$11.25/M
#26Qwen3.6 PlusAlibaba95.252.8 tok/s$1.13/M
#27DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek95.057.6 tok/s$0.544/M
#28GLM-5 (Reasoning)Z AI94.879.5 tok/s$1.55/M
#29Claude Opus 4.5 (Reasoning)Anthropic94.653.5 tok/s$10.94/M
#30MiniMax-M2.7MiniMax94.475 tok/s$0.525/M
#31Grok 4.20 0309 v2 (Reasoning)xAI94.3168.7 tok/s$3.00/M
#32MiMo-V2-ProXiaomi94.142.5 tok/s$1.50/M
#33GPT-5.2 Codex (xhigh)OpenAI93.9105.3 tok/s$4.81/M
#34MiMo-V2.5Xiaomi93.777.4 tok/s$0.175/M
#35GPT-5.4 mini (xhigh)OpenAI93.5176 tok/s$1.69/M
#36Grok 4.3 (medium)xAI93.3197.6 tok/s$1.56/M
#37Grok 4.20 0309 (Reasoning)xAI93.1166.5 tok/s$3.00/M
#38Gemini 3 Pro Preview (high)Google92.9n/a$4.50/M
#39GPT-5.4 (low)OpenAI92.763.6 tok/s$5.63/M
#40GPT-5.1 (high)OpenAI92.5121.2 tok/s$3.44/M
#41GLM-5-TurboZ AI92.3n/a-
#42Kimi K2.5 (Reasoning)Kimi92.131.7 tok/s$1.19/M
#43GPT-5.2 (medium)OpenAI92.0n/a$4.81/M
#44Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic91.840.9 tok/s$10.94/M
#45DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek91.6107.8 tok/s$0.175/M
#46Gemini 3 Flash Preview (Reasoning)Google91.4172.8 tok/s$1.13/M
#47DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek91.2n/a$0.175/M
#48Qwen3.6 27B (Reasoning)Alibaba91.054.7 tok/s$1.35/M
#49Qwen3.5 397B A17B (Reasoning)Alibaba90.851.8 tok/s$1.35/M
#50MiMo-V2-Omni-0327Xiaomi90.685.6 tok/s$0.800/M
#51GPT-5 (high)OpenAI90.4111.1 tok/s$3.44/M
#52GPT-5 Codex (high)OpenAI90.2171.1 tok/s$3.44/M
#53Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic90.057.9 tok/s$6.56/M
#54GPT-5.4 nano (xhigh)OpenAI89.8158.3 tok/s$0.463/M
#55Grok 4.3 (low)xAI89.7154.5 tok/s$1.56/M
#56GLM-5.1 (Non-reasoning)Z AI89.545.6 tok/s$2.15/M
#57KAT Coder Pro V2KwaiKAT89.3118.1 tok/s$0.525/M
#58Qwen3.6 35B A3B (Reasoning)Alibaba89.1159.9 tok/s$0.557/M
#59MiMo-V2-OmniXiaomi88.981.5 tok/s-
#60Gemini 3.5 Flash (minimal)Google88.7199.1 tok/s$3.38/M
#61Claude Opus 4.5 (Non-reasoning)Anthropic88.547.6 tok/s$10.94/M
#62GPT-5.1 Codex (high)OpenAI88.3182.1 tok/s$3.44/M
#63Claude 4.5 Sonnet (Reasoning)Anthropic88.150.1 tok/s$6.56/M
#64GLM 5V Turbo (Reasoning)Z AI87.9n/a-
#65Kimi K2.6 (Non-reasoning)Kimi87.739 tok/s$1.71/M
#66Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic87.561.7 tok/s$6.56/M
#67Step 3.7 FlashStepFun87.4385.5 tok/s$0.438/M
#68GLM-4.7 (Reasoning)Z AI87.279.2 tok/s$1.00/M
#69Qwen3.5 27B (Reasoning)Alibaba87.082.8 tok/s$0.825/M
#70Claude 4.1 Opus (Reasoning)Anthropic86.833.7 tok/s$32.81/M
#71GPT-5 (medium)OpenAI86.685.6 tok/s$3.44/M
#72TEHy3-preview (Reasoning)Tencent86.496 tok/s$0.200/M
#73MiniMax-M2.5MiniMax86.2202.9 tok/s$0.525/M
#74GPT-5.5 Instant (May 2026)OpenAI86.0n/a$11.25/M
#75DeepSeek V3.2 (Reasoning)DeepSeek85.8n/a$0.337/M
#76Qwen3.5 122B A10B (Reasoning)Alibaba85.6143.6 tok/s$1.10/M
#77Grok 4xAI85.4n/a$11.00/M
#78MiMo-V2-Flash (Feb 2026)Xiaomi85.2124.9 tok/s$0.150/M
#79Gemini 3 Pro Preview (low)Google85.1n/a$4.50/M
#80GPT-5 mini (high)OpenAI84.987.4 tok/s$0.688/M