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 · 301–350
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 301 | Grok 4.1 Fast (Non-reasoning) | SpaceXAI | 17.00 | — | — | — |
| 302 | K-EXAONE (Non-reasoning) | LG AI Research | 16.90 | — | — | — |
| 303 | Qwen3 Next 80B A3B (Reasoning) | Alibaba | 16.90 | $0.15 | $1.2 | 190 |
| 304 | GLM-4.6V (Reasoning) | Z AI | 16.90 | $0.3 | $0.9 | 67 |
| 305 | GPT-5.4 mini (Non-Reasoning) | OpenAI | 16.80 | $0.75 | $4.5 | 160 |
| 306 | GLM-4.5-Air | Z AI | 16.70 | $0.17 | $0.98 | 55 |
| 307 | Nova 2.0 Omni (low) | Amazon | 16.70 | $0.3 | $2.5 | — |
| 308 | Grok 4 Fast (Non-reasoning) | SpaceXAI | 16.60 | $0.2 | $0.5 | — |
| 309 | Mi:dm K 2.5 Pro | Korea Telecom | 16.60 | — | — | — |
| 310 | Ring-1T | InclusionAI | 16.30 | — | — | — |
| 311 | G9v3-3B | AI9Stars | 16.20 | $0 | $0 | — |
| 312 | Qwen3.5 4B (Non-reasoning) | Alibaba | 16.10 | $0.03 | $0.15 | 37 |
| 313 | Mistral Large 3 | Mistral | 15.90 | $0.5 | $1.5 | 32 |
| 314 | o3-mini (high) | OpenAI | 15.70 | $1.1 | $4.4 | 234 |
| 315 | INTELLECT-3 | Prime Intellect | 15.70 | — | — | — |
| 316 | GLM-4.7-Flash (Non-reasoning) | Z AI | 15.60 | $0.07 | $0.4 | 111 |
| 317 | GPT-5 (ChatGPT) | OpenAI | 15.40 | — | — | — |
| 318 | gpt-oss-20b (high) | OpenAI | 15.20 | $0.06 | $0.19 | 125 |
| 319 | Solar Open 100B (Reasoning) | Upstage | 15.20 | — | — | — |
| 320 | DeepSeek V3 0324 | DeepSeek | 15.20 | $0.27 | $1.12 | — |
| 321 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 15.20 | $0.1 | $0.4 | — | |
| 322 | Grok 3 Reasoning Beta | SpaceXAI | 15.20 | — | — | — |
| 323 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 15.00 | $0.07 | $0.3 | 328 |
| 324 | Mistral Small 3.1 | Mistral | 14.90 | $0.1 | $0.3 | 138 |
| 325 | gpt-oss-120b (low) | OpenAI | 14.90 | $0.15 | $0.59 | 138 |
| 326 | GPT-4.1 mini | OpenAI | 14.80 | $0.4 | $1.6 | 72 |
| 327 | Mistral Medium 3.1 | Mistral | 14.70 | $0.4 | $2 | 109 |
| 328 | Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 14.60 | $0.2 | $2.4 | 153 |
| 329 | MiniMax M1 40k | MiniMax | 14.50 | — | — | — |
| 330 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 14.50 | $0.05 | $0.2 | 222 |
| 331 | Llama 4 Maverick | Meta | 14.50 | $0.26 | $0.91 | 102 |
| 332 | Solar Pro 3 | Upstage | 14.50 | $0.15 | $0.6 | 160 |
| 333 | gpt-oss-20b (low) | OpenAI | 14.40 | $0.07 | $0.2 | 120 |
| 334 | Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 14.40 | $1.25 | $10 | 105 |
| 335 | Qwen3 VL 235B A22B Instruct | Alibaba | 14.40 | $0.4 | $1.6 | 49 |
| 336 | Granite 4.2 3B | IBM | 14.30 | $0.03 | $0.12 | 221 |
| 337 | GPT-5 mini (minimal) | OpenAI | 14.30 | $0.25 | $2 | 93 |
| 338 | DeepSeek V3 (Dec '24) | DeepSeek | 14.20 | $0.36 | $0.89 | — |
| 339 | Gemini 2.5 Flash (Non-reasoning) | 14.20 | $0.3 | $2.5 | 207 | |
| 340 | Ling 2.6 Flash | InclusionAI | 14.20 | — | — | — |
| 341 | K2-V2 (high) | MBZUAI Institute of Foundation Models | 14.20 | — | — | — |
| 342 | o1-mini | OpenAI | 14.00 | — | — | — |
| 343 | Qwen3 Next 80B A3B Instruct | Alibaba | 13.80 | $0.15 | $1.2 | 182 |
| 344 | GPT-4.5 (Preview) | OpenAI | 13.60 | — | — | — |
| 345 | Tri-21B-think Preview | Trillion Labs | 13.60 | — | — | — |
| 346 | Qwen3 Coder 30B A3B Instruct | Alibaba | 13.60 | $0.45 | $2.25 | 91 |
| 347 | Qwen3 235B A22B (Reasoning) | Alibaba | 13.50 | $0.7 | $8.4 | 57 |
| 348 | DiffusionGemma 26B A4B | 13.50 | — | — | — | |
| 349 | Qwen3 VL 30B A3B (Reasoning) | Alibaba | 13.40 | $0.2 | $2.4 | 111 |
| 350 | QwQ 32B | Alibaba | 13.40 | $0.66 | $1 | — |
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.