LLM Model Rankings Live
Live rankings of 660 large language models from 117 providers, aggregated from LMSys Chatbot Arena, OpenRouter, Artificial Analysis, and the Hugging Face open-source leaderboard. Updated every 6 hours — last refresh 35 min ago.
Powered by:
LMSys Arena
OpenRouter
Artificial Analysis
Hugging Face
Models tracked
660
20 with usage data
Providers
117
All major labs
#1 Arena ELO
claude-opus-4-6-search
1251 ELO
#1 Token share
Google: Gemini 2.5 Flash Lite
0.1%
LMSys Arena — Top 15 by ELO
Human-voted preference ratings from blind side-by-side comparisons on Chatbot Arena.
OpenRouter — Top 15 by Token Share
Real production usage share across 60+ inference providers on the OpenRouter network.
Artificial Analysis — Quality Index
Independent benchmark suite covering reasoning, knowledge, code, and instruction-following.
Quality vs. Price
Bubble chart — find the best value: top-left is high quality at low price.
Full leaderboard
All 660 ranked models, sortable by any column. Click a row to see history and full specs.
| Model | Provider | Arena # | ELO | OR # | Quality | Context | $/1M in | $/1M out |
|---|---|---|---|---|---|---|---|---|
| claude-opus-4-6-search | — | 1 | 1251 | — | — | — | — | — |
| claude-opus-4-6-thinking | — | 1 | 1502 | — | — | — | — | — |
| dreamina-seedance-2.0-720p | — | 1 | 1457 | — | — | — | — | — |
| Google: Gemini 2.5 Flash Lite MM | — | — | 1 | — | 1.0M | $0.100 | $0.40 | |
| gpt-image-2 (medium) | — | 1 | 1389 | — | — | — | — | — |
| chatgpt-image-latest-high-fidelity (20251216) | — | 2 | 1392 | — | — | — | — | — |
| claude-opus-4-7-thinking | — | 2 | 1500 | — | — | — | — | — |
| gemini-3.1-flash-image-preview (nano-banana-2) [web-search] | — | 2 | 1270 | — | — | — | — | — |
| gpt-5.5-search | — | 2 | 1239 | — | — | — | — | — |
| happyhorse-1.0 | — | 2 | 1435 | — | — | — | — | — |
| claude-opus-4-6 | — | 3 | 1498 | — | — | — | — | — |
| gemini-3-pro-image-preview-2k (nano-banana-pro) | — | 3 | 1243 | — | — | — | — | — |
| grok-imagine-image-quality (20260519) | — | 3 | 1388 | — | — | — | — | — |
| grok-imagine-video | — | 3 | 1265 | — | — | — | — | — |
| Owl Alpha | openrouter | — | — | 3 | — | 1.0M | — | — |
| veo-3.1-audio-1080p | — | 3 | 1372 | — | — | — | — | — |
| claude-opus-4-7 | — | 4 | 1492 | — | — | — | — | — |
| ernie-5.1 | — | 4 | 1226 | — | — | — | — | — |
| Google: Gemini 2.5 Flash MM | — | — | 4 | — | 1.0M | $0.30 | $2.50 | |
| gpt-image-1.5-high-fidelity | — | 4 | 1241 | — | — | — | — | — |
| kling-o3-pro | — | 4 | 1247 | — | — | — | — | — |
| sora-2-pro | — | 4 | 1368 | — | — | — | — | — |
| claude-sonnet-4-6-search | — | 5 | 1219 | — | — | — | — | — |
| gemini-3-pro-image-preview (nano-banana-pro) | — | 5 | 1232 | — | — | — | — | — |
| glm-5.1 | — | 5 | 1532 | — | — | — | — | — |
| kling-o1-pro | — | 5 | 1208 | — | — | — | — | — |
| muse-spark | — | 5 | 1489 | — | — | — | — | — |
| Qwen: Qwen3.5-Flash MM | qwen | — | — | 5 | — | 1.0M | $0.065 | $0.26 |
| veo-3.1-audio | — | 5 | 1366 | — | — | — | — | — |
| claude-sonnet-4-6 | — | 6 | 1524 | — | — | — | — | — |
| gemini-3.1-pro-grounding | — | 6 | 1216 | — | — | — | — | — |
| gemini-3.1-pro-preview | — | 6 | 1488 | — | — | — | — | — |
| grok-imagine-image-quality | — | 6 | 1228 | — | — | — | — | — |
| runway-gen4-aleph | — | 6 | 1204 | — | — | — | — | — |
| veo-3.1-fast-audio | — | 6 | 1364 | — | — | — | — | — |
| gemini-3-pro | — | 7 | 1486 | — | — | — | — | — |
| gpt-5.2-search | — | 7 | 1210 | — | — | — | — | — |
| gpt-5.5 | — | 7 | 1288 | — | — | — | — | — |
| grok-imagine-video-480p | — | 7 | 1383 | — | — | — | — | — |
| kimi-k2.6 | — | 7 | 1519 | — | — | — | — | — |
| OpenAI: GPT-4o-mini MM | openai | — | — | 7 | — | 128K | $0.15 | $0.60 |
| uni-1.1-max | — | 7 | 1192 | — | — | — | — | — |
| veo-3.1-fast-audio-1080p | — | 7 | 1364 | — | — | — | — | — |
| Gemini 3.1 Flash-Lite Preview MM | — | — | 8 | 34 | 1.0M | $0.25 | $1.50 | |
| gpt-5.2-chat-latest-20260210 | — | 8 | 1280 | — | — | — | — | — |
| gpt-5.4 | — | 8 | 1474 | — | — | — | — | — |
| gpt-5.5-high | — | 8 | 1481 | — | — | — | — | — |
| gpt-5.5-high (codex-harness) | — | 8 | 1519 | — | — | — | — | — |
| grok-4.20-multi-agent-beta-0309 | — | 8 | 1209 | — | — | — | — | — |
| grok-imagine-video-720p | — | 8 | 1357 | — | — | — | — | — |
| mai-image-2 | — | 8 | 1182 | — | — | — | — | — |
| claude-opus-4-5-20251101 | — | 9 | 1466 | — | — | — | — | — |
| DeepSeek: DeepSeek V3.2 | deepseek | — | — | 9 | — | 131K | $0.25 | $0.38 |
| gemini-3-pro-grounding | — | 9 | 1208 | — | — | — | — | — |
| gemini-3.5-flash | — | 9 | 1480 | — | — | — | — | — |
| uni-1.1 | — | 9 | 1176 | — | — | — | — | — |
| veo-3-fast-audio | — | 9 | 1349 | — | — | — | — | — |
| vidu-q3-pro | — | 9 | 1361 | — | — | — | — | — |
| gemini-3-flash-grounding | — | 10 | 1206 | — | — | — | — | — |
| gpt-5.4-high | — | 10 | 1480 | — | — | — | — | — |
| gpt-5.5 (codex-harness) | — | 10 | 1489 | — | — | — | — | — |
| gpt-5.5-xhigh (codex-harness) | — | 10 | 1503 | — | — | — | — | — |
| grok-imagine-image | — | 10 | 1173 | — | — | — | — | — |
| kling-v3-pro | — | 10 | 1360 | — | — | — | — | — |
| wan2.6-t2v | — | 10 | 1341 | — | — | — | — | — |
| DeepSeek V4 Flash | deepseek | — | — | 11 | 36 | 1.0M | $0.100 | $0.20 |
| Google: Gemini 3 Flash Preview MM | — | — | 12 | — | 1.0M | $0.50 | $3.00 | |
| Mistral: Mistral Nemo | mistralai | — | — | 14 | — | 131K | $0.020 | $0.030 |
| OpenAI: GPT-5 Mini MM | openai | — | — | 15 | — | 400K | $0.25 | $2.00 |
| OpenAI: GPT-4.1 Mini MM | openai | — | — | 16 | — | 1.0M | $0.40 | $1.60 |
| DeepSeek V4 Pro | deepseek | — | — | 17 | 39 | 1.0M | $0.43 | $0.87 |
| Ling 2.6 Flash | inclusionai | — | — | 19 | 26 | 262K | $0.010 | $0.030 |
| Mistral: Ministral 3 8B 2512 MM | mistralai | — | — | 20 | — | 262K | $0.15 | $0.15 |
| Qwen: Qwen3.6 Plus MM | qwen | — | — | 22 | — | 1.0M | $0.33 | $1.95 |
| Google: Gemini 2.0 Flash MM | — | — | 23 | — | 1.0M | $0.100 | $0.40 | |
| Z.ai: GLM 4 32B | z ai | — | — | 24 | — | 128K | $0.100 | $0.100 |
| Google: Gemini 3.1 Flash Lite MM | — | — | 25 | — | 1.0M | $0.25 | $1.50 | |
| Meta: Llama 3.1 70B Instruct | meta llama | — | — | 26 | — | 131K | $0.40 | $0.40 |
| Google: Gemini 2.5 Flash Lite Preview 09-2025 MM | — | — | 27 | — | 1.0M | $0.100 | $0.40 | |
| Google: Gemma 3 12B MM | — | — | 28 | — | 131K | $0.040 | $0.13 | |
| Google: Gemini 2.0 Flash Lite MM | — | — | 29 | — | 1.0M | $0.075 | $0.30 | |
| xAI: Grok 4.3 MM | x ai | — | — | 30 | — | 1.0M | $1.25 | $2.50 |
| Google: Gemma 3 4B MM | — | — | 31 | — | 131K | $0.040 | $0.080 | |
| Qwen: Qwen3 32B | qwen | — | — | 32 | — | 41K | $0.080 | $0.28 |
| OpenAI: GPT-4.1 Nano MM | openai | — | — | 33 | — | 1.0M | $0.100 | $0.40 |
| MiMo-V2-Flash | xiaomi | — | — | 34 | 30 | 262K | $0.100 | $0.30 |
| Meta: Llama 4 Maverick MM | meta llama | — | — | 43 | — | 1.0M | $0.15 | $0.60 |
| Sao10K: Llama 3 8B Lunaris | sao10k | — | — | 44 | — | 8K | $0.040 | $0.050 |
| DeepSeek: DeepSeek V3 | deepseek | — | — | 45 | — | 164K | $0.32 | $0.89 |
| OpenAI: GPT-5.4 MM | openai | — | — | 47 | — | 1.1M | $2.50 | $15.0 |
| Z.ai: GLM 4.5 Air | z ai | — | — | 48 | — | 131K | $0.13 | $0.85 |
| Qwen: Qwen3 VL 8B Instruct MM | qwen | — | — | 49 | — | 131K | $0.080 | $0.50 |
| OpenAI GPT Latest MM | openai | — | — | 50 | — | 1.1M | $5.00 | $30.0 |
| OpenAI: GPT-5.5 MM | openai | — | — | 51 | — | 1.1M | $5.00 | $30.0 |
| gpt-oss-20b OS | openai | — | — | 52 | — | 131K | $0.030 | $0.14 |
| Qwen: Qwen3 235B A22B Instruct 2507 | qwen | — | — | 54 | — | 262K | $0.071 | $0.100 |
| Qwen2.5 72B Instruct | qwen | — | — | 55 | — | 33K | $0.36 | $0.40 |
| Anthropic: Claude Sonnet 4.5 MM | anthropic | — | — | 56 | — | 1.0M | $3.00 | $15.0 |
| Mistral: Ministral 3 3B 2512 MM | mistralai | — | — | 57 | — | 131K | $0.100 | $0.100 |
| Meta: Llama 4 Scout MM | meta llama | — | — | 58 | — | 328K | $0.080 | $0.30 |
| DeepSeek: DeepSeek V3 0324 | deepseek | — | — | 60 | — | 164K | $0.20 | $0.77 |
| Qwen: Qwen3.5-9B MM | qwen | — | — | 61 | — | 262K | $0.040 | $0.15 |
| Qwen: Qwen2.5 7B Instruct | qwen | — | — | 62 | — | 33K | $0.040 | $0.100 |
| Gemini 2.5 Pro MM | — | — | 63 | 35 | 1.0M | $1.25 | $10.0 | |
| GPT-5.4 nano MM | openai | — | — | 64 | 38 | 400K | $0.20 | $1.25 |
| Anthropic: Claude 3.5 Haiku MM | anthropic | — | — | 66 | — | 200K | $0.80 | $4.00 |
| Mistral: Ministral 3 14B 2512 MM | mistralai | — | — | 67 | — | 262K | $0.20 | $0.20 |
| Qwen: Qwen3 VL 32B Instruct MM | qwen | — | — | 68 | — | 131K | $0.10 | $0.42 |
| gpt-oss-120b OS | openai | — | — | 69 | — | 131K | $0.039 | $0.18 |
| MoonshotAI: Kimi K2 0905 | moonshotai | — | — | 70 | — | 262K | $0.60 | $2.50 |
| Google: Gemma 3n 4B | — | — | 71 | — | 33K | $0.060 | $0.12 | |
| Google Gemini Pro Latest MM | — | — | 72 | — | 1.0M | $2.00 | $12.0 | |
| Gemini 3.1 Pro Preview MM | — | — | 73 | 57 | 1.0M | $2.00 | $12.0 | |
| Mistral: Mistral Small 3.2 24B MM | mistralai | — | — | 74 | — | 128K | $0.075 | $0.20 |
| Qwen: Qwen3.7 Max | qwen | — | — | 75 | — | 1.0M | $2.50 | $7.50 |
| xAI: Grok 4.20 MM | x ai | — | — | 76 | — | 2.0M | $1.25 | $2.50 |
| Z.ai: GLM 4.7 Flash | z ai | — | — | 77 | — | 203K | $0.060 | $0.40 |
| OpenAI: GPT-4o-mini (2024-07-18) MM | openai | — | — | 78 | — | 128K | $0.15 | $0.60 |
| LiquidAI: LFM2-24B-A2B | liquid | — | — | 79 | — | 33K | $0.030 | $0.12 |
| Meta: Llama Guard 4 12B MM | meta llama | — | — | 80 | — | 164K | $0.18 | $0.18 |
| Mistral: Mistral Small 4 MM | mistralai | — | — | 81 | — | 262K | $0.15 | $0.60 |
| Mistral: Mistral Small 3 | mistralai | — | — | 82 | — | 33K | $0.050 | $0.080 |
| OpenAI: gpt-oss-safeguard-20b | openai | — | — | 83 | — | 131K | $0.075 | $0.30 |
| MoonshotAI: Kimi K2.5 MM | moonshotai | — | — | 86 | — | 262K | $0.40 | $1.90 |
| OpenAI GPT Mini Latest MM | openai | — | — | 88 | — | 400K | $0.75 | $4.50 |
| GPT-5.4 mini MM | openai | — | — | 89 | 23 | 400K | $0.75 | $4.50 |
| Qwen: Qwen3.6 Flash MM | qwen | — | — | 90 | — | 1.0M | $0.19 | $1.13 |
| MiMo-V2.5 MM | xiaomi | — | — | 92 | 49 | 1.0M | $0.40 | $2.00 |
| MiMo-V2-Omni MM | xiaomi | — | — | 93 | 43 | 262K | $0.40 | $2.00 |
| Google: Gemma 3 27B MM | — | — | 94 | — | 131K | $0.080 | $0.16 | |
| NVIDIA: Nemotron 3 Nano 30B A3B | nvidia | — | — | 96 | — | 262K | $0.050 | $0.20 |
| Qwen: Qwen3.6 Max Preview | qwen | — | — | 98 | — | 262K | $1.04 | $6.24 |
| OpenAI: GPT-4o MM | openai | — | — | 99 | — | 128K | $2.50 | $10.0 |
| Perplexity: Sonar MM | perplexity | — | — | 100 | — | 127K | $1.00 | $1.00 |
| Z.ai: GLM 4.7 | z ai | — | — | 103 | — | 203K | $0.40 | $1.75 |
| Qwen: Qwen3.5-27B MM | qwen | — | — | 104 | — | 262K | $0.20 | $1.56 |
| Mistral: Devstral Small 1.1 MM | mistralai | — | — | 106 | — | 131K | $0.100 | $0.30 |
| OpenAI: GPT-5 Chat MM | openai | — | — | 107 | — | 128K | $1.25 | $10.0 |
| MiniMax-M2.7 | minimax | — | — | 108 | 50 | 197K | $0.28 | $1.20 |
| Qwen: Qwen3 14B | qwen | — | — | 110 | — | 41K | $0.100 | $0.24 |
| OpenAI: GPT-5.3-Codex MM | openai | — | — | 111 | — | 400K | $1.75 | $14.0 |
| DeepSeek: DeepSeek V3.1 | deepseek | — | — | 112 | — | 164K | $0.21 | $0.79 |
| Mercury 2 | inception | — | — | 113 | 33 | 128K | $0.25 | $0.75 |
| Amazon: Nova 2 Lite MM | amazon | — | — | 114 | — | 1.0M | $0.30 | $2.50 |
| Mistral: Mistral Medium 3.5 MM | mistralai | — | — | 115 | — | 262K | $1.50 | $7.50 |
| Qwen: Qwen3.5 Plus 2026-02-15 MM | qwen | — | — | 116 | — | 1.0M | $0.26 | $1.56 |
| Mistral: Mistral Large 3 2512 MM | mistralai | — | — | 117 | — | 262K | $0.50 | $1.50 |
| OpenAI: GPT-4o (2024-11-20) MM | openai | — | — | 118 | — | 128K | $2.50 | $10.0 |
| MoonshotAI: Kimi K2 0711 | moonshotai | — | — | 119 | — | 131K | $0.57 | $2.30 |
| OpenAI: o3 Mini MM | openai | — | — | 121 | — | 200K | $1.10 | $4.40 |
| DeepSeek: DeepSeek V3.2 Exp | deepseek | — | — | 123 | — | 164K | $0.27 | $0.41 |
| Qwen: Qwen3 VL 235B A22B Instruct MM | qwen | — | — | 125 | — | 262K | $0.20 | $0.88 |
| Xiaomi: MiMo-V2-Pro | xiaomi | — | — | 128 | — | 1.0M | $1.00 | $3.00 |
| OpenAI: GPT-3.5 Turbo | openai | — | — | 129 | — | 16K | $0.50 | $1.50 |
| Qwen: Qwen3 VL 30B A3B Instruct MM | qwen | — | — | 130 | — | 131K | $0.13 | $0.52 |
| GLM-5 | z ai | — | — | 131 | 50 | 203K | $0.60 | $1.92 |
| Anthropic: Claude 3 Haiku MM | anthropic | — | — | 132 | — | 200K | $0.25 | $1.25 |
| DeepSeek R1 0528 | deepseek | — | — | 133 | 27 | 164K | $0.50 | $2.15 |
| DeepSeek: DeepSeek V3.1 Terminus | deepseek | — | — | 134 | — | 164K | $0.27 | $0.95 |
| ByteDance Seed: Seed 1.6 Flash MM | bytedance seed | — | — | 135 | — | 262K | $0.075 | $0.30 |
| Qwen: Qwen3.5 397B A17B MM | qwen | — | — | 136 | — | 262K | $0.39 | $2.34 |
| OpenAI: GPT-5 Nano MM | openai | — | — | 137 | — | 400K | $0.050 | $0.40 |
| Amazon: Nova Micro 1.0 | amazon | — | — | 138 | — | 128K | $0.035 | $0.14 |
| Qwen: Qwen3 235B A22B | qwen | — | — | 139 | — | 131K | $0.45 | $1.82 |
| MythoMax 13B | gryphe | — | — | 141 | — | 4K | $0.060 | $0.060 |
| IBM: Granite 4.1 8B | ibm granite | — | — | 142 | — | 131K | $0.050 | $0.100 |
| Google: Gemma 2 27B | — | — | 143 | — | 8K | $0.65 | $0.65 | |
| IBM: Granite 4.0 Micro | ibm granite | — | — | 144 | — | 131K | $0.017 | $0.11 |
| Mistral: Mistral Small 3.1 24B MM | mistralai | — | — | 145 | — | 128K | $0.35 | $0.55 |
| Anthropic: Claude Opus 4.5 MM | anthropic | — | — | 146 | — | 200K | $5.00 | $25.0 |
| EssentialAI: Rnj 1 Instruct | essentialai | — | — | 147 | — | 33K | $0.15 | $0.15 |
| DeepSeek: R1 | deepseek | — | — | 149 | — | 64K | $0.70 | $2.50 |
| Qwen: Qwen3 235B A22B Thinking 2507 | qwen | — | — | 150 | — | 131K | $0.15 | $1.50 |
| OpenAI: GPT-5.1 MM | openai | — | — | 151 | — | 400K | $1.25 | $10.0 |
| MoonshotAI Kimi Latest MM | moonshotai | — | — | 152 | — | 262K | $0.73 | $3.49 |
| MoonshotAI: Kimi K2.6 MM | moonshotai | — | — | 153 | — | 262K | $0.73 | $3.49 |
| Z.ai: GLM 4.6 | z ai | — | — | 154 | — | 203K | $0.43 | $1.74 |
| OpenAI: GPT-4o (2024-08-06) MM | openai | — | — | 155 | — | 128K | $2.50 | $10.0 |
| Perplexity: Sonar Pro MM | perplexity | — | — | 156 | — | 200K | $3.00 | $15.0 |
| NVIDIA: Nemotron 3 Super | nvidia | — | — | 157 | — | 262K | $0.090 | $0.45 |
| Qwen: Qwen3 30B A3B Thinking 2507 | qwen | — | — | 158 | — | 131K | $0.080 | $0.40 |
| StepFun: Step 3.5 Flash | stepfun | — | — | 160 | — | 262K | $0.090 | $0.30 |
| AionLabs: Aion-2.0 | aion labs | — | — | 161 | — | 131K | $0.80 | $1.60 |
| Mistral: Mistral Medium 3.1 MM | mistralai | — | — | 162 | — | 131K | $0.40 | $2.00 |
| OpenAI: o4 Mini MM | openai | — | — | 164 | — | 200K | $1.10 | $4.40 |
| OpenAI: GPT-5.4 Image 2 MM | openai | — | — | 167 | — | 272K | $8.00 | $15.0 |
| MiniMax: MiniMax M2.5 | minimax | — | — | 168 | — | 197K | $0.15 | $1.15 |
| Mistral: Mistral 7B Instruct v0.1 | mistralai | — | — | 170 | — | 3K | $0.11 | $0.19 |
| Gemini 3.5 Flash MM | — | — | 172 | 55 | 1.0M | $1.50 | $9.00 | |
| Google Gemini Flash Latest MM | — | — | 173 | — | 1.0M | $1.50 | $9.00 | |
| Qwen: Qwen2.5 VL 72B Instruct MM | qwen | — | — | 174 | — | 32K | $0.25 | $0.75 |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) MM | — | — | 175 | — | 66K | $0.50 | $3.00 | |
| MiniMax: MiniMax M2-her | minimax | — | — | 176 | — | 66K | $0.30 | $1.20 |
| Nous: Hermes 4 70B | nousresearch | — | — | 177 | — | 131K | $0.13 | $0.40 |
| Ling-2.6-1T | inclusionai | — | — | 178 | 34 | 262K | $0.075 | $0.63 |
| ByteDance Seed: Seed-2.0-Mini MM | bytedance seed | — | — | 180 | — | 262K | $0.100 | $0.40 |
| TheDrummer: Cydonia 24B V4.1 | thedrummer | — | — | 181 | — | 131K | $0.30 | $0.50 |
| Anthropic Claude Sonnet Latest MM | anthropic | — | — | 184 | — | 1.0M | $3.00 | $15.0 |
| MiMo-V2.5-Pro | xiaomi | — | — | 185 | 54 | 1.0M | $1.00 | $3.00 |
| Anthropic: Claude Sonnet 4.6 MM | anthropic | — | — | 186 | — | 1.0M | $3.00 | $15.0 |
| NVIDIA: Nemotron Nano 9B V2 | nvidia | — | — | 187 | — | 131K | $0.040 | $0.16 |
| GLM-5-Turbo | z ai | — | — | 188 | 47 | 203K | $1.20 | $4.00 |
| Anthropic: Claude Opus Latest MM | anthropic | — | — | 189 | — | 1.0M | $5.00 | $25.0 |
| Anthropic: Claude Opus 4.7 MM | anthropic | — | — | 190 | — | 1.0M | $5.00 | $25.0 |
| OpenAI: GPT-4.1 MM | openai | — | — | 191 | — | 1.0M | $2.00 | $8.00 |
| Qwen: Qwen3 30B A3B Instruct 2507 | qwen | — | — | 192 | — | 262K | $0.090 | $0.30 |
| Meta: Llama 3 8B Instruct | meta llama | — | — | 193 | — | 8K | $0.040 | $0.040 |
| Phi-4 | microsoft | — | — | 194 | 10 | 16K | $0.065 | $0.14 |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview) MM | — | — | 195 | — | 66K | $2.00 | $12.0 | |
| Qwen: Qwen3.5-35B-A3B MM | qwen | — | — | 196 | — | 262K | $0.14 | $1.00 |
| TheDrummer: UnslopNemo 12B | thedrummer | — | — | 197 | — | 33K | $0.40 | $0.40 |
| Nous: Hermes 3 70B Instruct | nousresearch | — | — | 198 | — | 131K | $0.30 | $0.30 |
| Meta: Llama 3.2 11B Vision Instruct MM | meta llama | — | — | 199 | — | 131K | $0.24 | $0.24 |
| Qwen: Qwen3 Max | qwen | — | — | 200 | — | 262K | $0.78 | $3.90 |
| DeepSeek: R1 Distill Qwen 32B | deepseek | — | — | 202 | — | 33K | $0.29 | $0.29 |
| Microsoft: Phi 4 Mini Instruct | microsoft | — | — | 203 | — | 128K | $0.080 | $0.35 |
| Anthropic Claude Haiku Latest MM | anthropic | — | — | 204 | — | 200K | $1.00 | $5.00 |
| Anthropic: Claude Haiku 4.5 MM | anthropic | — | — | 205 | — | 200K | $1.00 | $5.00 |
| OpenAI: GPT-4 Turbo MM | openai | — | — | 207 | — | 128K | $10.0 | $30.0 |
| Qwen: Qwen3.5 Plus 2026-04-20 MM | qwen | — | — | 208 | — | 1.0M | $0.30 | $1.80 |
| WizardLM-2 8x22B | microsoft | — | — | 210 | — | 66K | $0.62 | $0.62 |
| Cohere: Command R7B (12-2024) | cohere | — | — | 211 | — | 128K | $0.037 | $0.15 |
| GLM-5.1 | z ai | — | — | 212 | 51 | 203K | $0.98 | $3.08 |
| Mistral Large 2411 MM | mistralai | — | — | 214 | — | 131K | $2.00 | $6.00 |
| Qwen: Qwen3.6 35B A3B MM | qwen | — | — | 215 | — | 262K | $0.15 | $1.00 |
| Mistral Large MM | mistralai | — | — | 216 | — | 128K | $2.00 | $6.00 |
| Cohere: Command R (08-2024) | cohere | — | — | 217 | — | 128K | $0.15 | $0.60 |
| Mistral: Devstral 2 2512 MM | mistralai | — | — | 218 | — | 262K | $0.40 | $2.00 |
| Arcee AI: Trinity Mini | arcee ai | — | — | 219 | — | 131K | $0.045 | $0.15 |
| Mistral: Codestral 2508 MM | mistralai | — | — | 220 | — | 256K | $0.30 | $0.90 |
| OpenAI: GPT-5.1 Chat MM | openai | — | — | 221 | — | 128K | $1.25 | $10.0 |
| Nous: Hermes 4 405B | nousresearch | — | — | 222 | — | 131K | $1.00 | $3.00 |
| OpenAI: GPT-5.2 MM | openai | — | — | 223 | — | 400K | $1.75 | $14.0 |
| Qwen: Qwen3.6 27B MM | qwen | — | — | 224 | — | 262K | $0.30 | $3.20 |
| Qwen: Qwen3 Coder Plus | qwen | — | — | 225 | — | 1.0M | $0.65 | $3.25 |
| Trinity Large Thinking | arcee ai | — | — | 227 | 32 | 262K | $0.22 | $0.85 |
| GLM 5V Turbo MM | z ai | — | — | 228 | 43 | 203K | $1.20 | $4.00 |
| OpenAI: GPT-5.5 Pro MM | openai | — | — | 229 | — | 1.1M | $30.0 | $180.0 |
| MiniMax: MiniMax-01 MM | minimax | — | — | 230 | — | 1.0M | $0.20 | $1.10 |
| Qwen2.5 Coder 32B Instruct | qwen | — | — | 232 | — | 33K | $0.66 | $1.00 |
| Sao10K: Llama 3.3 Euryale 70B | sao10k | — | — | 233 | — | 131K | $0.65 | $0.75 |
| ByteDance Seed: Seed-2.0-Lite MM | bytedance seed | — | — | 234 | — | 262K | $0.25 | $2.00 |
| xAI: Grok Build 0.1 MM | x ai | — | — | 235 | — | 256K | $1.00 | $2.00 |
| TheDrummer: Rocinante 12B | thedrummer | — | — | 237 | — | 33K | $0.17 | $0.43 |
| Mistral: Mixtral 8x22B Instruct MM | mistralai | — | — | 238 | — | 66K | $2.00 | $6.00 |
| Qwen: Qwen3 30B A3B | qwen | — | — | 240 | — | 41K | $0.090 | $0.45 |
| OpenAI: GPT-5.1-Codex MM | openai | — | — | 241 | — | 400K | $1.25 | $10.0 |
| Amazon: Nova Lite 1.0 MM | amazon | — | — | 243 | — | 300K | $0.060 | $0.24 |
| Qwen: Qwen3 Next 80B A3B Instruct | qwen | — | — | 244 | — | 262K | $0.090 | $1.10 |
| Google: Gemma 4 26B A4B MM | — | — | 245 | — | 262K | $0.060 | $0.33 |
About these rankings
Four data sources, refreshed every 6 hours, zero manual curation.
What data sources power the AI Gear Base LLM rankings?
We aggregate live rankings from four authoritative sources: OpenRouter (real-world token usage across 60+ inference providers), LMSys Chatbot Arena (human-voted ELO ratings), Artificial Analysis (independent quality + speed benchmarks), and the Hugging Face open-source leaderboard. Rankings refresh every 6 hours from all sources, so the data you see is never more than 6 hours stale.
How many LLMs and providers are tracked?
660 models from 117 providers — including OpenAI, Anthropic, Google, Meta, Mistral, xAI, DeepSeek, Alibaba/Qwen, Cohere, and the leading open-source labs. Every model carries pricing, context window, modalities, and ranking history so you can compare both proprietary frontier models and open-weights releases on equal footing.
How often are the rankings updated?
Every 6 hours, fully automated. A Cloudflare cron trigger pulls fresh data from the OpenRouter and Hugging Face public APIs, while Apify Actors scrape the LMSys Arena and Artificial Analysis leaderboards on the same cadence and post the results to our ingestion webhook. All snapshots are written to a time-series table so we can show 7-day, 30-day, and all-time trend lines on each model's detail page.
Why do rankings differ between sources?
Each source measures a different thing. LMSys Arena captures human preference (which model do real users like more?), Artificial Analysis measures objective quality + throughput on standardised benchmarks, OpenRouter reflects actual production usage by paying API customers, and Hugging Face tracks community popularity. A truly great model usually ranks highly across all four — which is why we show every score side-by-side in the comparison table instead of inventing a single "AI Gear Base score" that hides the nuance.