Data
Core
Compare
Methodology
vi
en
← Back to leaderboard
Compare AI models
Pick up to 4 models to compare metrics side by side.
Add a model…
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) - Anthropic
Claude Opus 4.8 (Adaptive Reasoning, Max Effort) - Anthropic
GPT-5.5 (xhigh) - OpenAI
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) - Anthropic
GPT-5.4 (xhigh) - OpenAI
GLM-5.2 (max) - Zhipu AI
Gemini 3.5 Flash - Google
Gemini 3.1 Pro Preview - Google
GPT-5.2 (xhigh) - OpenAI
Qwen3.7 Max - Alibaba
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) - Anthropic
Claude Opus 4.5 - Anthropic
Gemini 3 Pro Preview (high) - Google
GPT-5.1 - OpenAI
GPT-5.2 Chat - OpenAI
Gemini 3 Flash Preview - Google
GPT-5.5 - OpenAI
DeepSeek V4 Pro (Reasoning, Max Effort) - DeepSeek
GPT-5 Codex - OpenAI
MiniMax M3 - minimax
MiMo-V2.5-Pro - xiaomi
GPT-5 Chat - OpenAI
Muse Spark - Meta
Kimi K2.7 Code - Kimi
GPT-5.1-Codex - OpenAI
Kimi K2.6 - Kimi
GLM 4.7 - Zhipu AI
Claude 4.5 Sonnet (Reasoning) - Anthropic
DeepSeek V3.2 - DeepSeek
Grok 4 - xAI
DeepSeek V4 Flash (Reasoning, Max Effort) - DeepSeek
GLM 5.1 - Zhipu AI
GPT-5.4 mini (xhigh) - OpenAI
GPT-5 Mini - OpenAI
MiMo-V2-Flash (Reasoning) - Xiaomi
Qwen3.7 Plus - Alibaba
Qwen3.6 Plus - Alibaba
GPT-5.4 nano (xhigh) - OpenAI
GPT-5.3 Codex (xhigh) - OpenAI
Grok Build 0.1 0616 - xAI
GPT-5.1-Codex-Mini - OpenAI
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) - Anthropic
Claude 4.1 Opus (Reasoning) - Anthropic
MiniMax M2.7 - minimax
Grok 4.1 Fast (Reasoning) - xAI
Qwen3.6 27B - Alibaba
o3 - OpenAI
GPT-5.5 (Non-reasoning) - OpenAI
Claude Opus 4.7 (Non-reasoning, High Effort) - Anthropic
KAT-Coder-Pro V1 - KwaiKAT
MiniMax M2.1 - minimax
Claude 4.5 Haiku (Reasoning) - Anthropic
Nemotron 3 Ultra 550B A55B (Reasoning) - NVIDIA
DeepSeek V4 Pro (Reasoning, High Effort) - DeepSeek
Claude Opus 4.5 (Non-reasoning) - Anthropic
Grok 4 Fast (Reasoning) - xAI
MiMo-V2-Pro - Xiaomi
MiMo-V2.5 - xiaomi
GPT-5.2 Codex (xhigh) - OpenAI
Claude 4 Opus (Reasoning) - Anthropic
Qwen3.6 Max Preview - Alibaba
Gemini 2.5 Pro - Google
Claude 4 Sonnet (Reasoning) - Anthropic
DeepSeek V3.1 Terminus - DeepSeek
o4 Mini High - OpenAI
GLM 5 - Zhipu AI
Grok 4.3 - xAI
GPT-5.4 - OpenAI
MiniMax M2 - minimax
Qwen3.5 397B A17B - Alibaba
K-EXAONE (Reasoning) - LG AI Research
GLM 4.6 - Zhipu AI
DeepSeek V3.2 Speciale - DeepSeek
GLM 5 Turbo - Zhipu AI
Kimi K2.5 (Reasoning) - Kimi
Claude Opus 4.6 (Non-reasoning, High Effort) - Anthropic
DeepSeek V4 Flash (Reasoning, High Effort) - DeepSeek
Doubao Seed Code - ByteDance Seed
Qwen3.5-122B-A10B - Alibaba
Grok 4.20 0309 v2 (Reasoning) - xAI
Grok 4.20 0309 (Reasoning) - xAI
MiMo-V2-Omni-0327 - Xiaomi
Mistral Medium 3.5 - Mistral
Claude Sonnet 4.6 (Non-reasoning, High Effort) - Anthropic
Grok 3 mini Reasoning (high) - xAI
Nova 2.0 Omni (medium) - Amazon
DeepSeek V3.1 - DeepSeek
Nova 2.0 Pro Preview (medium) - Amazon
Gemini 2.5 Flash Preview (Sep '25) (Reasoning) - Google
ERNIE 5.0 Thinking Preview - Baidu
KAT Coder Pro V2 - KwaiKAT
GLM-5.1 (Non-reasoning) - Zhipu AI
Apriel-v1.5-15B-Thinker - ServiceNow
Qwen3.6 35B A3B - Alibaba
MiMo-V2-Omni - Xiaomi
Apriel-v1.6-15B-Thinker - ServiceNow
Ring-2.6-1T - inclusionai
Gemini 3.5 Flash (minimal) - Google
Kimi K2.6 (Non-reasoning) - Kimi
GLM 5V Turbo - Zhipu AI
Gemma 4 31B (free) - Google
Claude 3.7 Sonnet (Reasoning) - Anthropic
Nova 2.0 Lite (medium) - Amazon
Qwen3.5-27B - Alibaba
MiniMax M2.5 - minimax
Qwen3 Next 80B A3B Thinking - Alibaba
Hy3-preview (Reasoning) - Tencent
GPT-5.5 Instant (May 2026) - OpenAI
Gemini 3 Flash Preview (Non-reasoning) - Google
Magistral Medium 1.2 - Mistral
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) - NVIDIA
MiMo-V2-Flash (Feb 2026) - Xiaomi
MiMo-V2-Flash (Non-reasoning) - Xiaomi
o3 Pro - OpenAI
Seed-OSS-36B-Instruct - ByteDance Seed
Step 3.7 Flash - stepfun
GLM-5 (Non-reasoning) - Zhipu AI
DeepSeek R1 0528 (May '25) - DeepSeek
DeepSeek V3.2 (Non-reasoning) - DeepSeek
Qwen3.5 397B A17B (Non-reasoning) - Alibaba
Ring-1T - InclusionAI
GPT-5 Nano - OpenAI
GLM 4.6V - Zhipu AI
GPT-5.2 (Non-reasoning) - OpenAI
Gemini 2.5 Pro Preview (Mar' 25) - Google
Qwen3 Max Thinking - Alibaba
DeepSeek V4 Pro (Non-reasoning) - DeepSeek
GLM-4.7 (Non-reasoning) - Zhipu AI
GLM 4.5 - Zhipu AI
INTELLECT-3 - Prime Intellect
Claude 4.5 Sonnet (Non-reasoning) - Anthropic
Kimi K2 0905 - Kimi
Qwen3.5 Omni Plus - Alibaba
Gemma 4 26B A4B (free) - Google
GLM 4.5 Air - Zhipu AI
GPT-5.4 Nano - OpenAI
GPT-5.4 Mini - OpenAI
Qwen3 235B A22B Thinking 2507 - Alibaba
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) - NVIDIA
Gemini 2.5 Flash - Google
Kimi K2.5 (Non-reasoning) - Kimi
Qwen3.5-35B-A3B - Alibaba
dm K 2.5 Pro - Korea Telecom
Qwen3.6 27B (Non-reasoning) - Alibaba
Qwen3.5 27B (Non-reasoning) - Alibaba
o1 - OpenAI
gpt-oss-120b (free) - OpenAI
DeepSeek V4 Flash (Non-reasoning) - DeepSeek
Grok 4.3 (Non-reasoning) - xAI
Gemini 3.1 Flash Lite - Google
JT-35B-Flash - China Mobile
DeepSeek V3.1 Terminus (Non-reasoning) - DeepSeek
Claude 4.1 Opus (Non-reasoning) - Anthropic
Claude 4 Sonnet (Non-reasoning) - Anthropic
Qwen3 VL 30B A3B Thinking - Alibaba
Qwen3 235B A22B - Alibaba
Qwen3.5 122B A10B (Non-reasoning) - Alibaba
MiMo-V2.5-Pro (Non-reasoning) - Xiaomi
Claude 4 Opus (Non-reasoning) - Anthropic
GPT-5.4 (Non-reasoning) - OpenAI
GLM-4.6 (Non-reasoning) - Zhipu AI
Kimi K2 - Kimi
Motif-2-12.7B-Reasoning - Motif Technologies
DeepSeek V3.1 (Non-reasoning) - DeepSeek
Qwen3 4B 2507 (Reasoning) - Alibaba
Claude 4.5 Haiku (Non-reasoning) - Anthropic
MiniMax M1 80k - MiniMax
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) - Google
Grok 3 - xAI
o3 Mini High - OpenAI
Magistral Small 1.2 - Mistral
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) - Google
Qwen3 VL 235B A22B Thinking - Alibaba
Qwen3.5-9B - Alibaba
Llama Nemotron Super 49B v1.5 (Reasoning) - NVIDIA
Grok Code Fast 1 - xAI
Ling-2.6-1T - inclusionai
Hy3-preview (Non-reasoning) - Tencent
Step 3.5 Flash 2603 - StepFun
HyperCLOVA X SEED Think (32B) - Naver
Step 3.5 Flash - stepfun
EXAONE 4.0 32B (Reasoning) - LG AI Research
Mercury 2 - inception
Ling-1T - InclusionAI
Gemma 4 31B (Non-reasoning) - Google
Falcon-H1R-7B - TII UAE
Trinity Large Thinking - arcee-ai
DeepSeek R1 (Jan '25) - DeepSeek
Ring-flash-2.0 - InclusionAI
Qwen3.6 35B A3B (Non-reasoning) - Alibaba
GPT-5.1 (Non-reasoning) - OpenAI
Gemini 2.5 Flash (Non-reasoning) - Google
Qwen3 32B - Alibaba
Qwen3 VL 32B Instruct - Alibaba
gpt-oss-20b (free) - OpenAI
Qwen3 Omni 30B A3B (Reasoning) - Alibaba
Qwen3.5 35B A3B (Non-reasoning) - Alibaba
NVIDIA Nemotron Nano 12B v2 VL (Reasoning) - NVIDIA
EXAONE 4.5 33B - LG AI Research
o1-preview - OpenAI
Claude 3.7 Sonnet (Non-reasoning) - Anthropic
GLM 4.7 Flash - Zhipu AI
Olmo 3.1 32B Think - Allen Institute for AI
GLM 4.5V - Zhipu AI
Qwen3 30B A3B - Alibaba
GPT-4.1 - OpenAI
GPT-4.1 Mini - OpenAI
Qwen3 Coder 480B A35B (free) - Alibaba
Hermes 4 - Llama-3.1 70B (Reasoning) - Nous Research
K-EXAONE (Non-reasoning) - LG AI Research
Grok 4.20 0309 (Non-reasoning) - xAI
GPT-5 (ChatGPT) - OpenAI
Gemini 2.5 Pro Preview (May' 25) - Google
HyperNova 60B 2605 - Multiverse Computing
DeepSeek R1 Distill Qwen 32B - DeepSeek
Gemma 4 12B (Reasoning) - Google
Hermes 4 - Llama-3.1 405B (Reasoning) - Nous Research
NVIDIA Nemotron Nano 9B V2 (Reasoning) - NVIDIA
DeepSeek R1 0528 Qwen3 8B - DeepSeek
Grok 4.20 0309 v2 (Non-reasoning) - xAI
Grok 4 Fast (Non-reasoning) - xAI
Ling-flash-2.0 - InclusionAI
Qwen3 30B A3B Thinking 2507 - Alibaba
Qwen3.5 9B (Non-reasoning) - Alibaba
Nemotron Cascade 2 30B A3B - NVIDIA
Llama 3.3 Nemotron Super 49B v1 (Reasoning) - NVIDIA
Qwen3 Coder Next - Alibaba
GPT-5 mini (minimal) - OpenAI
DeepSeek V3 0324 - DeepSeek
Qwen3.5 4B (Reasoning) - Alibaba
Mistral Small 4 - Mistral
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) - NVIDIA
Olmo 3 32B Think - Allen Institute for AI
North Mini Code (free) - Cohere
Grok 4.1 Fast (Non-reasoning) - xAI
Mistral Large 3 - Mistral
Gemini 2.5 Flash Lite - Google
GPT-5 (minimal) - OpenAI
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) - Google
Solar Pro 2 (Reasoning) - Upstage
Gemma 4 26B A4B (Non-reasoning) - Google
Devstral 2 - Mistral
Qwen3 14B - Alibaba
Mistral Medium 3.1 - Mistral
DeepSeek R1 Distill Qwen 14B - DeepSeek
Nova 2.0 Pro Preview (Non-reasoning) - Amazon
Ling-2.6-flash - inclusionai
DeepSeek R1 Distill Llama 70B - DeepSeek
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) - NVIDIA
Qwen3.5 Omni Flash - Alibaba
o1-pro - OpenAI
K2 Think V2 - MBZUAI Institute of Foundation Models
JT-MINI - China Mobile
Magistral Medium 1 - Mistral
Olmo 3 7B Think - Allen Institute for AI
Qwen3 14B (Non-reasoning) - Alibaba
Sonar Reasoning Pro - Perplexity
GPT-5.4 nano (Non-Reasoning) - OpenAI
Devstral Small 2 - Mistral
Qwen3.5 4B (Non-reasoning) - Alibaba
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) - NVIDIA
Magistral Small 1 - Mistral
LongCat Flash Lite - LongCat
Gemini 2.0 Flash Thinking Experimental (Jan '25) - Google
Claude 3.5 Sonnet (Oct '24) - Anthropic
Qwen3 Coder 30B A3B Instruct - Alibaba
QwQ 32B - Alibaba
GPT-5.4 mini (Non-Reasoning) - OpenAI
Gemini 2.0 Pro Experimental (Feb '25) - Google
Nova 2.0 Lite (Non-reasoning) - Amazon
Mistral Medium 3 - Mistral
Nova 2.0 Omni (Non-reasoning) - Amazon
ERNIE 4.5 300B A47B - Baidu
Llama 4 Maverick - Meta
GLM-4.7-Flash (Non-reasoning) - Zhipu AI
GPT-4o (March 2025, chatgpt-4o-latest) - OpenAI
Solar Open 100B (Reasoning) - Upstage
Nemotron 3 Nano Omni 30B A3B Reasoning - NVIDIA
Solar Pro 3 - upstage
Gemini 1.5 Pro (Sep '24) - Google
Kimi Linear 48B A3B Instruct - Kimi
Claude 3.5 Sonnet (June '24) - Anthropic
Claude 3 Opus - Anthropic
Ministral 3 14B - Mistral
K2-V2 (low) - MBZUAI Institute of Foundation Models
Gemini 2.0 Flash (Feb '25) - Google
MiniMax M1 40k - MiniMax
GLM-4.6V (Non-reasoning) - Zhipu AI
GPT-4o (May '24) - OpenAI
o1-mini - OpenAI
DeepSeek R1 Distill Llama 8B - DeepSeek
Nova Premier - Amazon
DeepSeek V3 (Dec '24) - DeepSeek
Tri-21B-think Preview - Trillion Labs
Qwen3.5 2B (Reasoning) - Alibaba
GPT-4.5 (Preview) - OpenAI
Devstral Small (Jul '25) - Mistral
Qwen3 235B A22B (Non-reasoning) - Alibaba
Ling-mini-2.0 - InclusionAI
Gemma 4 12B (Non-reasoning) - Google
Ministral 3 8B - Mistral
EXAONE 4.0 32B (Non-reasoning) - LG AI Research
Exaone 4.0 1.2B (Reasoning) - LG AI Research
Gemini 2.5 Flash-Lite (Non-reasoning) - Google
Mistral Small 3.2 - Mistral
GPT-4 Turbo - OpenAI
Solar Pro 2 (Non-reasoning) - Upstage
Qwen3 VL 8B Thinking - Alibaba
Gemma 4 E4B (Reasoning) - Google
Mistral Small 4 (Non-reasoning) - Mistral
Claude 3.5 Haiku - Anthropic
GPT-5 nano (minimal) - OpenAI
MiniCPM5-1B (Reasoning) - OpenBMB
Sarvam 105B (high) - Sarvam
Qwen3.5 2B (Non-reasoning) - Alibaba
Devstral Small (May '25) - Mistral
Sonar - Perplexity
MiniCPM5-1B (Non-reasoning) - OpenBMB
Qwen3 4B (Reasoning) - Alibaba
Gemini 1.5 Pro (May '24) - Google
Qwen3 VL 4B Instruct - Alibaba
Olmo 3 7B Instruct - Allen Institute for AI
Qwen3 32B (Non-reasoning) - Alibaba
GPT-4.1 Nano - OpenAI
Devstral Medium - Mistral
Gemini 2.0 Flash (experimental) - Google
Qwen3.5 0.8B (Non-reasoning) - Alibaba
Qwen2.5 72B Instruct - Alibaba
Reka Flash 3 - Reka AI
Qwen3 1.7B (Reasoning) - Alibaba
Hermes 4 - Llama-3.1 405B (Non-reasoning) - Nous Research
Mistral Large 2 (Nov '24) - Mistral
Qwen2.5 Max - Alibaba
Llama 4 Scout - Meta
Nanbeige4.1-3B - Nanbeige
GPT-4o (Nov '24) - OpenAI
Qwen3 30B A3B (Non-reasoning) - Alibaba
Qwen3 8B - Alibaba
GPT-4o (Aug '24) - OpenAI
Step3 VL 10B - StepFun
Granite 4.1 30B - IBM
Gemma 4 E2B (Reasoning) - Google
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) - NVIDIA
GPT-4 - OpenAI
Gemini 1.0 Ultra - Google
Qwen3 8B (Non-reasoning) - Alibaba
QwQ 32B-Preview - Alibaba
Gemma 4 E4B (Non-reasoning) - Google
Command A - Cohere
NVIDIA Nemotron 3 Nano 4B - NVIDIA
Gemini 2.0 Flash-Lite (Feb '25) - Google
GLM-4.5V (Non-reasoning) - Zhipu AI
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) - NVIDIA
GPT-4o-mini - OpenAI
Gemini 2.0 Flash-Lite (Preview) - Google
Llama Nemotron Super 49B v1.5 (Non-reasoning) - NVIDIA
Qwen3.5 0.8B (Reasoning) - Alibaba
Llama 3.3 70B Instruct (free) - Meta
LFM2.5-8B-A1B - Liquid AI
Llama 3.1 Nemotron Instruct 70B - NVIDIA
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) - NVIDIA
Llama 3.1 Tulu3 405B - Allen Institute for AI
Gemma 3 27B - Google
GPT-4o (ChatGPT) - OpenAI
Gemini 1.5 Flash (Sep '24) - Google
Grok 2 (Dec '24) - xAI
Ministral 3 3B - Mistral
Hermes 4 - Llama-3.1 70B (Non-reasoning) - Nous Research
Phi 4 - Microsoft
Granite 4.1 8B - IBM
Mistral Small 3.1 - Mistral
DeepSeek R1 Distill Qwen 1.5B - DeepSeek
Nova Pro - Amazon
Claude 2.1 - Anthropic
Grok Beta - xAI
Qwen2.5 Instruct 32B - Alibaba
Llama 3.1 Instruct 405B - Meta
Exaone 4.0 1.2B (Non-reasoning) - LG AI Research
Qwen2.5 Coder 32B Instruct - Alibaba
Granite 4.0 H Small - IBM
Claude 2.0 - Anthropic
Pixtral Large - Mistral
Nova Lite - Amazon
LFM2 8B A1B - Liquid AI
DeepSeek-V2.5 (Dec '24) - DeepSeek
Qwen3 4B (Non-reasoning) - Alibaba
Gemma 3 12B - Google
Sarvam 30B (high) - Sarvam
Gemini 2.0 Flash Thinking Experimental (Dec '24) - Google
DeepSeek-V2.5 - DeepSeek
Olmo 3.1 32B Instruct - Allen Institute for AI
Gemma 4 E2B (Non-reasoning) - Google
Mistral Saba - Mistral
Mistral Small 3 - Mistral
R1 1776 - Perplexity
Reka Flash (Sep '24) - Reka AI
Qwen2.5 Turbo - Alibaba
Llama 3.1 70B Instruct - Meta
Llama 3.2 Instruct 90B (Vision) - Meta
Solar Mini - Upstage
GPT-3.5 Turbo Instruct - OpenAI
Grok-1 - xAI
Qwen2 Instruct 72B - Alibaba
Llama 3.1 8B Instruct - Meta
Mistral Large 2 (Jul '24) - Mistral
Jamba Reasoning 3B - AI21 Labs
Gemini 1.5 Flash-8B - Google
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) - Nous Research
DeepSeek-Coder-V2 - DeepSeek
Hermes 3 - Llama-3.1 70B - Nous Research
Jamba 1.5 Large - AI21 Labs
Nova Micro - Amazon
Jamba 1.6 Large - AI21 Labs
LFM2 24B A2B - Liquid AI
Gemini 1.5 Flash (May '24) - Google
Qwen3 0.6B (Reasoning) - Alibaba
Jamba 1.7 Large - AI21 Labs
Claude 3 Sonnet - Anthropic
Mistral Small (Sep '24) - Mistral
Gemma 3n E4B Instruct Preview (May '25) - Google
OLMo 2 32B - Allen Institute for AI
Phi-4 Multimodal Instruct - Microsoft
Qwen2.5 Coder Instruct 7B - Alibaba
Mixtral 8x22B Instruct - Mistral
Mistral Large (Feb '24) - Mistral
Llama 2 Chat 7B - Meta
Claude Instant - Anthropic
Qwen1.5 Chat 110B - Alibaba
Llama 3.2 3B Instruct (free) - Meta
Gemma 3n E4B Instruct - Google
Claude 3 Haiku - Anthropic
LFM2 2.6B - Liquid AI
Phi 4 Mini Instruct - Microsoft
PALM-2 - Google
Phi-3 Mini Instruct 3.8B - Microsoft
Gemma 3 4B - Google
Mistral Small (Feb '24) - Mistral
Mistral Medium - Mistral
DeepSeek-V2-Chat - DeepSeek
Granite 4.0 H 1B - IBM
Llama 3 Instruct 70B - Meta
LFM 40B - Liquid AI
Arctic Instruct - Snowflake
Qwen Chat 72B - Alibaba
Granite 4.0 Micro - IBM
Granite 4.1 3B - IBM
OLMo 2 7B - Allen Institute for AI
Gemini 1.0 Pro - Google
DeepSeek Coder V2 Lite Instruct - DeepSeek
Llama 3.2 11B Vision Instruct - Meta
Molmo 7B-D - Allen Institute for AI
Granite 4.0 1B - IBM
MiniCPM-V 4.6 1.3B - OpenBMB
Llama 2 Chat 13B - Meta
Llama 2 Chat 70B - Meta
Gemma 3n E2B Instruct - Google
DeepSeek LLM 67B Chat (V1) - DeepSeek
OpenChat 3.5 (1210) - OpenChat
DBRX Instruct - Databricks
Sarvam M (Reasoning) - Sarvam
Command-R+ (Apr '24) - Cohere
Qwen3 0.6B (Non-reasoning) - Alibaba
Granite 3.3 8B (Non-reasoning) - IBM
LFM2.5-1.2B-Thinking - Liquid AI
LFM2.5-1.2B-Instruct - Liquid AI
Jamba 1.5 Mini - AI21 Labs
Qwen3 1.7B (Non-reasoning) - Alibaba
Jamba 1.6 Mini - AI21 Labs
Gemma 3 270M - Google
Apertus 70B Instruct - Swiss AI Initiative
Mixtral 8x7B Instruct - Mistral
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) - Nous Research
Jamba 1.7 Mini - AI21 Labs
Llama 65B - Meta
Qwen Chat 14B - Alibaba
Mistral 7B Instruct - Mistral
Command-R (Mar '24) - Cohere
Molmo2-8B - Allen Institute for AI
LFM2 1.2B - Liquid AI
Gemma 3 1B Instruct - Google
Llama 3 8B Instruct - Meta
Granite 4.0 H 350M - IBM
LFM2.5-VL-1.6B - Liquid AI
Apertus 8B Instruct - Swiss AI Initiative
Tiny Aya Global - Cohere
Llama 3.2 1B Instruct - Meta
Granite 4.0 350M - IBM
GPT-5.3-Codex - OpenAI
Claude Opus 4.6 - Anthropic
GPT-5.1-Codex-Max - OpenAI
Kimi K2 Thinking - Moonshot AI
Gemini 2.5 Pro Preview 05-06 - Google
GPT-4o - OpenAI
Gemini 2.0 Pro exp-02-05 - Google
claude-3-5-sonnet-20241022 - Anthropic
Qwen2.5-Coder-32B-Instruct - Alibaba
gemini-exp-1206 - Google
gemini-2.0-flash-exp - Google
DeepSeek Chat V3 (prev) - DeepSeek
Codestral 25.01 - Mistral
DeepSeek R1 - DeepSeek
DeepSeek R1 + claude-3-5-sonnet-20241022 - Anthropic
qwen-max-2025-01-25 - Alibaba
gemini-2.0-flash-thinking-exp-01-21 - Google
chatgpt-4o-latest (2025-02-15) - OpenAI
claude-3-7-sonnet-20250219 (no thinking) - Anthropic
claude-3-7-sonnet-20250219 (32k thinking tokens) - Anthropic
gpt-4.5-preview - OpenAI
QwQ-32B + Qwen 2.5 Coder Instruct - Alibaba
command-a-03-2025-quality - Cohere
gemma-3-27b-it - Google
Gemini 2.5 Pro Preview 03-25 - Google
chatgpt-4o-latest (2025-03-29) - OpenAI
gemini-2.5-flash-preview-04-17 (default) - Google
Qwen3 235B A22B diff, no think, Alibaba API - Alibaba
claude-sonnet-4-20250514 (no thinking) - Anthropic
claude-sonnet-4-20250514 (32k thinking) - Anthropic
claude-opus-4-20250514 (no think) - Anthropic
claude-opus-4-20250514 (32k thinking) - Anthropic
gemini-2.5-flash-preview-05-20 (no think) - Google
gemini-2.5-flash-preview-05-20 (24k think) - Google
gemini-2.5-pro-preview-06-05 (default think) - Google
gemini-2.5-pro-preview-06-05 (32k think) - Google
DeepSeek R1 (0528) - DeepSeek
o3 (high) + gpt-4.1 - OpenAI
DeepSeek-V3.2-Exp (Reasoner) - DeepSeek
DeepSeek-V3.2-Exp (Chat) - DeepSeek
GPT-4 1106 - OpenAI
GPT-4 0314 - OpenAI
Select models above to start comparing.