LLM rankings, places 151 to 213
- models measured
- 213
- lead over #2
- +1.6
- median
- 18.5
Leader on AA Intelligence Index · read October 21
As of October 21, 2026, Anthropic Claude Opus 5.5 leads 213 models on the Artificial Analysis Intelligence Index with 57.6. Every other column is one category read from its own public board; a model a board never measured says "No data". Nothing is estimated.
63 of 213 shown
JSON| Rank | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| 151 | Trinity Large Thinking Arcee AI | 10.8 | 5.4 | 1.0 | 75.2%* | No data | No data | 1137 | $0.80 |
| 152 | Mercury 2 Inception | 10.8 | 0.0 | 1.6 | 77.0%* | No data | No data | 1036 | $0.75 |
| 153 | Gemini 2.5 Flash Lite Google | 10.4 | No data | No data | 70.2% | No data | 79.1% | No data | $0.40 |
| 154 | GPT-4.1 Mini OpenAI | 10.2 | 28.5 | No data | 67.9% | 44.7% | 77.2% | 997 | $1.60 |
| 155 | gpt-oss-20b OpenAI | 10.0 | No data | No data | 68.9% | 65.3% | 71.6% | 853 | $0.09 |
| 156 | 9.9 | No data | No data | 77.2%* | No data | 83.6%* | No data | $1.90 | |
| 157 | DeepSeek V3 0324 DeepSeek | 9.7 | 42.0 | 0.8 | 61.6% | 37.8% | 79.5% | No data | $1.14 |
| 158 | 9.6 | 60.4 | No data | 51.6%* | No data | 70.6%* | 1087 | $0.28 | |
| 159 | 9.6 | No data | No data | 75.9%* | No data | 82.4%* | No data | $1.10 | |
| 160 | 9.5 | No data | No data | No data | No data | No data | No data | $1.00 | |
| 161 | Llama 4 Maverick Meta Llama | 9.3 | 18.1 | 0.6 | 69.4% | No data | 79.4% | 871 | $0.6525 |
| 162 | Mistral Large 3 2512 Mistral AI | 9.3 | No data | 1.0 | 68.4% | No data | 79.8% | 1162 | $1.50 |
| 163 | Nova Premier 1.0 Amazon | 9.2 | No data | No data | 56.9%* | No data | 73.3%* | 835 | $12.50 |
| 164 | Mistral Medium 3.1 Mistral AI | 9.2 | No data | 1.9 | 58.8%* | No data | 75.3% | 1133 | $2.00 |
| 165 | Qwen3 Coder Next Qwen | 9.2 | No data | 0.9 | 73.7%* | No data | No data | No data | $0.80 |
| 166 | Mistral Medium 3 Mistral AI | 9.0 | No data | No data | 57.8%* | No data | 76.0%* | 1079 | $2.00 |
| 167 | Nemotron 3 Nano 30B A3B NVIDIA | 8.9 | No data | 1.0 | 75.7%* | No data | 79.4%* | No data | $0.24 |
| 168 | Devstral 2 2512 Mistral AI | 8.6 | 53.8 | 2.3 | No data | No data | No data | No data | $2.00 |
| 169 | GPT-4o (2024-11-20) OpenAI | 8.4 | 18.2 | No data | 53.8% | 6.3% | 72.6% | No data | $10.00 |
| 170 | 7.9 | No data | No data | 72.0%* | No data | 80.7%* | No data | $0.60 | |
| 171 | GPT-4.1 Nano OpenAI | 7.8 | 8.9 | No data | 50.8% | 28.9% | 63.5% | 973 | $0.40 |
| 172 | Solar Pro 3 Upstage | 7.8 | No data | 1.4 | 72.4%* | No data | No data | No data | $0.60 |
| 173 | GPT-4o (2024-08-06) OpenAI | 7.7 | 23.1 | No data | 49.2%* | 6.4% | 74.1% | No data | $10.00 |
| 174 | Llama 3.3 70B Instruct Meta Llama | 7.7 | No data | No data | 47.4%* | 5.1% | 71.3%* | No data | $0.32 |
| 175 | Sonar Perplexity | 7.7 | No data | No data | 47.1%* | No data | 68.9%* | No data | $1.00 |
| 176 | Qwen2.5 72B Instruct Qwen | 7.7 | No data | No data | 49.1%* | 8.1% | 72.0%* | No data | $0.40 |
| 177 | Mistral Large 2407 Mistral AI | 7.6 | No data | No data | 49.0%* | 8.5% | 68.3%* | No data | $6.00 |
| 178 | Sonar Pro Perplexity | 7.6 | No data | No data | 57.8%* | No data | 75.5%* | No data | $15.00 |
| 179 | Qwen3 30B A3B Qwen | 7.6 | No data | No data | 61.7%* | 62.8% | 77.7%* | 955 | $0.50 |
| 180 | GLM 4.5V Z.ai | 7.6 | No data | No data | 68.4%* | No data | 78.8%* | No data | $1.80 |
| 181 | N Hermes 4 405B Nous Research | 7.5 | No data | No data | No data | No data | No data | No data | $3.00 |
| 182 | 7.5 | No data | No data | 55.6%* | 62.2% | 80.5%* | No data | $0.30 | |
| 183 | Qwen3 32B Qwen | 7.3 | 40.0 | No data | 65.7%* | 66.9% | 79.8%* | No data | $0.28 |
| 184 | GPT-4o (2024-05-13) OpenAI | 7.3 | No data | No data | 50.2% | 6.3% | 74.0%* | No data | $15.00 |
| 185 | Qwen3 VL 8B Instruct Qwen | 7.3 | No data | No data | 57.9%* | No data | 74.9%* | No data | $0.75 |
| 186 | Nova Pro 1.0 Amazon | 7.0 | No data | No data | 49.9%* | No data | 69.1%* | 796 | $3.20 |
| 187 | GPT-4 Turbo OpenAI | 7.0 | No data | No data | No data | No data | 69.4%* | No data | $30.00 |
| 188 | Llama 3.1 8B Instruct Meta Llama | 6.9 | No data | No data | 27.0%* | 1.7% | 47.6%* | No data | $0.08 |
| 189 | 6.7 | 30.5 | No data | 41.7%* | No data | 63.5%* | No data | $1.00 | |
| 190 | GPT-4 OpenAI | 6.7 | 22.4 | No data | 34.9%* | No data | 56.2%* | No data | $60.00 |
| 191 | Nova Lite 1.0 Amazon | 6.7 | No data | No data | 43.3%* | No data | 59.0%* | No data | $0.24 |
| 192 | Mistral Small 3 Mistral AI | 6.7 | No data | No data | 46.2%* | No data | 65.2%* | No data | $0.08 |
| 193 | N Hermes 3 70B Instruct Nous Research | 6.7 | No data | No data | 40.1%* | No data | 57.1%* | No data | $0.70 |
| 194 | GPT-4o-mini OpenAI | 6.7 | No data | No data | 44.2% | No data | 62.7% | No data | $0.60 |
| 195 | Qwen3 14B Qwen | 6.7 | No data | No data | 63.8%* | 66.4% | 77.4%* | No data | $0.24 |
| 196 | Llama 3.1 70B Instruct Meta Llama | 6.6 | No data | No data | 44.2%* | 3.6% | 67.6%* | No data | $0.40 |
| 197 | Llama 4 Scout Meta Llama | 6.5 | 9.1 | 0.5 | 47.0% | 7.8% | 69.6% | 750 | $0.30 |
| 198 | Saba Mistral AI | 6.5 | No data | No data | 42.4%* | No data | 61.1%* | No data | $0.60 |
| 199 | Reka Flash 3 Reka | 6.4 | No data | No data | 52.9%* | No data | 66.9%* | No data | $0.20 |
| 200 | Ministral 3 14B 2512 Mistral AI | 6.0 | No data | 1.1 | No data | No data | No data | 1081 | $0.20 |
| 201 | Nova Micro 1.0 Amazon | 5.9 | No data | No data | 35.8%* | No data | 53.1%* | No data | $0.14 |
| 202 | Phi 4 Microsoft | 5.9 | No data | No data | 56.1%* | 13.8% | 71.4%* | No data | $0.14 |
| 203 | Mistral Large Mistral AI | 5.8 | No data | No data | 47.7% | No data | 69.7% | No data | $6.00 |
| 204 | Llama 3.2 3B Instruct Meta Llama | 5.7 | No data | No data | 25.5%* | No data | 34.7%* | No data | $0.335 |
| 205 | Mixtral 8x22B Instruct Mistral AI | 5.7 | No data | No data | 33.2%* | No data | 53.7%* | No data | $6.00 |
| 206 | Ministral 3 8B 2512 Mistral AI | 5.5 | No data | 0.6 | No data | No data | No data | 1065 | $0.15 |
| 207 | GPT-3.5 Turbo OpenAI | 5.5 | No data | No data | 30.6% | No data | 46.2%* | No data | $1.50 |
| 208 | Granite 4.0 Micro IBM Granite | 5.1 | No data | No data | 28.3%* | 2.8% | 44.7%* | No data | $0.112 |
| 209 | Gemma 3 27B Google | 4.9 | 4.9 | 0.1 | 47.7%* | 22.5% | 66.9%* | No data | $0.35 |
| 210 | Gemma 3 4B Google | 4.8 | No data | No data | 23.2%* | 7.5% | 41.7%* | No data | $0.05 |
| 211 | Llama 3.2 1B Instruct Meta Llama | 4.8 | No data | No data | 23.9%* | 0.6% | 20.0%* | No data | $0.201 |
| 212 | Ministral 3 3B 2512 Mistral AI | 4.8 | No data | 0.8 | No data | No data | No data | 1028 | $0.10 |
| 213 | Gemma 3 12B Google | 3.8 | No data | 0.1 | 39.5%* | 16.7% | 59.5%* | No data | $0.15 |
First on that board Top 5% Top 15% Top 35% of the models it measured
Overall: Artificial Analysis Intelligence Index. Coding: our Vibe Coding Index, with its benchmarks as dots. Agentic: AA Agentic Index. Reasoning: GPQA Diamond as run by Vals AI, or by Epoch AI or Artificial Analysis where Vals has no result (marked *). Math: OTIS Mock AIME. Knowledge: MMLU Pro, from Vals AI or Artificial Analysis (marked *). Web design: Design Arena, websites, Elo. Price: OpenRouter, per million output tokens.