LLM leaderboard
Every tracked language model by intelligence, with what it costs and how fast it answers.
ranked by intelligence · 611 models · updated Aug 30 · 251–300
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 251 | DeepSeek V3.1 (Reasoning) | DeepSeek | 21.00 | $0.59 | $1.69 | — |
| 252 | Qwen3 VL 235B A22B (Reasoning) | Alibaba | 20.90 | $0.4 | $4 | 56 |
| 253 | Nova 2.0 Lite (high) | Amazon | 20.80 | $0.3 | $2.5 | 173 |
| 254 | Apriel-v1.6-15B-Thinker | ServiceNow | 20.80 | $0 | $0 | — |
| 255 | GPT-5.1 (Non-reasoning) | OpenAI | 20.70 | $1.25 | $10 | 90 |
| 256 | Qwen3.5 9B (Non-reasoning) | Alibaba | 20.60 | $0.17 | $0.25 | 95 |
| 257 | EXAONE 4.5 33B | LG AI Research | 20.50 | — | — | — |
| 258 | Qwen3.5 4B (Reasoning) | Alibaba | 20.40 | $0.03 | $0.15 | 43 |
| 259 | Gemma 4 26B A4B (Non-reasoning) | 20.40 | $0.13 | $0.4 | 70 | |
| 260 | DeepSeek R1 0528 (May '25) | DeepSeek | 20.40 | $1.35 | $3 | — |
| 261 | Gemini 2.5 Flash (Reasoning) | 20.30 | $0.3 | $2.5 | 210 | |
| 262 | North Mini Code | Cohere | 20.20 | $0 | $0 | 104 |
| 263 | GPT-5 nano (high) | OpenAI | 20.10 | $0.05 | $0.4 | 163 |
| 264 | Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 19.90 | $0.23 | $2.3 | 68 |
| 265 | Nova 2.0 Pro Preview (low) | Amazon | 19.80 | $1.25 | $10 | 128 |
| 266 | GLM-4.5 (Reasoning) | Z AI | 19.70 | — | — | — |
| 267 | Mistral Small 4 (Reasoning) | Mistral | 19.70 | $0.15 | $0.6 | 149 |
| 268 | Kimi K2 | Kimi | 19.70 | $0.57 | $2.3 | 40 |
| 269 | GPT-4.1 | OpenAI | 19.60 | $2 | $8 | 166 |
| 270 | Granite 4.2 8B | IBM | 19.60 | $0.06 | $0.25 | 145 |
| 271 | Qwen3 Max (Preview) | Alibaba | 19.40 | $1.2 | $6 | 60 |
| 272 | Devstral 2 | Mistral | 19.20 | $0 | $0 | 44 |
| 273 | o3-mini | OpenAI | 19.20 | $1.1 | $4.4 | 242 |
| 274 | Qwen3.5 Omni Flash | Alibaba | 19.20 | $0.1 | $0.8 | 250 |
| 275 | GPT-5 nano (medium) | OpenAI | 19.20 | $0.05 | $0.4 | 159 |
| 276 | Nova 2.0 Lite (medium) | Amazon | 19.20 | $0.3 | $2.5 | 163 |
| 277 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | 19.10 | — | — | — | |
| 278 | o1-pro | OpenAI | 19.10 | $150 | $600 | — |
| 279 | JT-MINI | China Mobile | 18.80 | — | — | — |
| 280 | Trinity Large Thinking | Arcee AI | 18.70 | $0.23 | $0.88 | 196 |
| 281 | DeepSeek R1 (Jan '25) | DeepSeek | 18.60 | $2 | $4 | — |
| 282 | Grok 3 | SpaceXAI | 18.60 | $4 | $20 | — |
| 283 | Seed-OSS-36B-Instruct | ByteDance Seed | 18.50 | $0.21 | $0.57 | 35 |
| 284 | Qwen3 235B A22B 2507 Instruct | Alibaba | 18.40 | $0.23 | $0.92 | 58 |
| 285 | HyperNova 60B 2605 | Multiverse Computing | 18.30 | $0.04 | $0.14 | 351 |
| 286 | Qwen3 Coder 480B A35B Instruct | Alibaba | 18.20 | $1.5 | $7.5 | 59 |
| 287 | Qwen3 VL 32B (Reasoning) | Alibaba | 18.10 | $0.16 | $0.64 | 89 |
| 288 | Sonar Reasoning Pro | Perplexity | 18.00 | — | — | — |
| 289 | Nova 2.0 Lite (low) | Amazon | 18.00 | $0.3 | $2.5 | 158 |
| 290 | Magistral Medium 1.2 | Mistral | 18.00 | — | — | — |
| 291 | MiniMax M1 80k | MiniMax | 17.90 | $0.55 | $2.2 | — |
| 292 | Nemotron Cascade 2 30B A3B | NVIDIA | 17.80 | — | — | — |
| 293 | GPT-5.4 nano (Non-Reasoning) | OpenAI | 17.80 | $0.2 | $1.25 | 161 |
| 294 | Gemini 2.5 Flash Preview (Reasoning) | 17.70 | — | — | — | |
| 295 | Devstral Small 2 | Mistral | 17.70 | $0 | $0 | 138 |
| 296 | K2 Think V2 | MBZUAI Institute of Foundation Models | 17.40 | — | — | — |
| 297 | LongCat Flash Lite | LongCat | 17.40 | — | — | — |
| 298 | GPT-5 (minimal) | OpenAI | 17.30 | $1.25 | $10 | 77 |
| 299 | o1-preview | OpenAI | 17.20 | $16.5 | $66 | — |
| 300 | HyperCLOVA X SEED Think (32B) | Naver | 17.20 | — | — | — |
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.