LLM leaderboard
Every tracked language model by intelligence, with what it costs and how fast it answers.
ranked by intelligence · 690 models · updated Oct 15 · 301–350
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 301 | Grok 3 mini Reasoning (High) | SpaceXAI | 14.60 | $0.3 | $0.5 | 65 |
| 302 | Gemini 2.5 Pro Preview (May' 25) | 14.50 | $1.25 | $10 | — | |
| 303 | DeepSeek V3.2 Speciale | DeepSeek | 14.50 | — | — | — |
| 304 | K-EXAONE (Reasoning) | LG AI Research | 14.40 | — | — | — |
| 305 | ERNIE 5.0 Thinking Preview | Baidu | 14.30 | — | — | — |
| 306 | Nova 2.0 Pro Preview (Medium) | Amazon | 14.20 | $1.375 | $11 | 126 |
| 307 | Grok 4.20 0309 v2 (Non-reasoning) | SpaceXAI | 14.20 | $1.25 | $2.5 | 111 |
| 308 | Mistral Medium 3.5 | Mistral | 14.20 | $1.5 | $7.5 | 151 |
| 309 | Gemma 4 12B (Reasoning) | 14.20 | $0.1 | $0.3 | 112 | |
| 310 | Grok Code Fast 1 | SpaceXAI | 14.10 | — | — | — |
| 311 | Grok 4.3 (Non-reasoning) | SpaceXAI | 14.00 | $1.25 | $2.5 | 94 |
| 312 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | 13.90 | $0.28 | $0.42 | — |
| 313 | Gemma 4 31B (Non-reasoning) | 13.90 | $0.165 | $0.4 | 48 | |
| 314 | DeepSeek V3.1 Terminus (Non-reasoning) | DeepSeek | 13.90 | $0.27 | $1 | 41 |
| 315 | Apriel-v1.5-15B-Thinker | ServiceNow | 13.80 | $0 | $0 | — |
| 316 | DeepSeek V3.1 (Non-reasoning) | DeepSeek | 13.70 | $0.56 | $1.68 | 98 |
| 317 | Nova 2.0 Omni (Medium) | Amazon | 13.60 | $0.3 | $2.5 | — |
| 318 | DeepSeek V3.1 (Reasoning) | DeepSeek | 13.50 | $0.58 | $1.68 | 119 |
| 319 | Nova 2.0 Lite (High) | Amazon | 13.40 | $0.33 | $2.75 | 179 |
| 320 | Apriel-v1.6-15B-Thinker | ServiceNow | 13.40 | $0 | $0 | — |
| 321 | Qwen3 VL 235B A22B (Reasoning) | Alibaba | 13.40 | — | — | — |
| 322 | Qwen3.5 9B (Non-reasoning) | Alibaba | 13.30 | $0.17 | $0.25 | 100 |
| 323 | GPT-5.1 (Non-reasoning) | OpenAI | 13.30 | $1.25 | $10 | 107 |
| 324 | EXAONE 4.5 33B (Reasoning) | LG AI Research | 13.20 | — | — | — |
| 325 | Gemini 2.5 Flash (Reasoning) | 13.10 | $0.3 | $2.5 | 206 | |
| 326 | Command A+ | Cohere | 13.10 | $0 | $0 | 182 |
| 327 | Qwen3.5 4B (Reasoning) | Alibaba | 13.10 | $0.03 | $0.15 | 20 |
| 328 | Gemma 4 26B A4B (Non-reasoning) | 13.10 | $0.13 | $0.4 | 93 | |
| 329 | DeepSeek R1 0528 (May '25) | DeepSeek | 13.10 | $1.35 | $3 | 32 |
| 330 | GPT-5 nano (High) | OpenAI | 13.00 | $0.05 | $0.4 | 159 |
| 331 | Nemotron 3.5 Lightning | NVIDIA | 12.90 | $0.06 | $0.2 | 302 |
| 332 | GLM-4.5 (Reasoning) | Z AI | 12.80 | — | — | — |
| 333 | Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 12.80 | $0.3 | $0.9 | 146 |
| 334 | Nova 2.0 Pro Preview (Low) | Amazon | 12.80 | $1.375 | $11 | 120 |
| 335 | Granite 4.2 30B | IBM | 12.70 | $0.16 | $0.65 | 75 |
| 336 | GPT-4.1 | OpenAI | 12.70 | $2 | $8 | 152 |
| 337 | Kimi K2 | Kimi | 12.70 | $0.57 | $2.3 | 55 |
| 338 | Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 12.70 | $0.23 | $2.3 | 85 |
| 339 | Qwen3 Max (Preview) | Alibaba | 12.60 | — | — | — |
| 340 | o3-mini | OpenAI | 12.50 | $1.1 | $4.4 | 181 |
| 341 | MiniCPM5-2B | OpenBMB | 12.50 | — | — | — |
| 342 | Qwen3.5 Omni Flash | Alibaba | 12.50 | $0.1 | $0.8 | 223 |
| 343 | GPT-5 nano (Medium) | OpenAI | 12.50 | $0.05 | $0.4 | 155 |
| 344 | Nova 2.0 Lite (Medium) | Amazon | 12.50 | $0.33 | $2.75 | 181 |
| 345 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 12.40 | — | — | — | |
| 346 | o1-pro | OpenAI | 12.40 | $150 | $600 | — |
| 347 | Mercury 2.5 | Inception | 12.30 | $0.25 | $0.75 | 594 |
| 348 | JT-MINI | China Mobile | 12.20 | — | — | — |
| 349 | Grok 3 | SpaceXAI | 12.10 | $3 | $15 | 100 |
| 350 | Seed-OSS-36B-Instruct | ByteDance Seed | 12.10 | $0.21 | $0.57 | 41 |
what intelligence means
A composite of nine independent evaluations covering reasoning, coding, agentic work and knowledge. Higher is better. It is versioned, so scores are comparable within a version rather than across all time.