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 · 351–400
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 351 | Qwen3 235B A22B 2507 Instruct | Alibaba | 12.00 | $0.22 | $0.88 | 44 |
| 352 | Qwen3 Coder 480B A35B Instruct | Alibaba | 11.90 | $0.3 | $1.8 | 97 |
| 353 | Qwen3 VL 32B (Reasoning) | Alibaba | 11.90 | — | — | — |
| 354 | Sonar Reasoning Pro | Perplexity | 11.80 | — | — | — |
| 355 | Nova 2.0 Lite (Low) | Amazon | 11.80 | $0.33 | $2.75 | 183 |
| 356 | Magistral Medium 1.2 | Mistral | 11.80 | — | — | — |
| 357 | HyperNova 60B 2605 (High, Based on gpt-oss-120b) | Multiverse Computing | 11.70 | — | — | — |
| 358 | Gemini 2.5 Flash Preview (Reasoning) | 11.70 | — | — | — | |
| 359 | Nemotron Cascade 2 30B A3B | NVIDIA | 11.70 | — | — | — |
| 360 | MiniMax M1 80k | MiniMax | 11.70 | $0.55 | $2.2 | 67 |
| 361 | GPT-5.4 nano (Non-reasoning) | OpenAI | 11.70 | $0.2 | $1.25 | 162 |
| 362 | gpt-oss-120b (High) | OpenAI | 11.60 | $0.15 | $0.59 | 221 |
| 363 | K2 Think V2 | Institute of Foundation Models | 11.50 | — | — | — |
| 364 | LongCat Flash Lite | LongCat | 11.50 | — | — | — |
| 365 | o1-preview | OpenAI | 11.40 | $16.5 | $66 | — |
| 366 | DeepSeek R1 (Jan '25) | DeepSeek | 11.40 | $2 | $4 | 150 |
| 367 | HyperCLOVA X SEED Think (32B) | Naver | 11.40 | — | — | — |
| 368 | GPT-5 (Minimal) | OpenAI | 11.40 | $1.25 | $10 | 76 |
| 369 | Mistral Small 4 (Reasoning) | Mistral | 11.30 | $0.15 | $0.6 | 166 |
| 370 | Grok 4.1 Fast (Non-reasoning) | SpaceXAI | 11.30 | — | — | — |
| 371 | Qwen3.5 9B (Reasoning) | Alibaba | 11.20 | $0.135 | $0.2 | 65 |
| 372 | K-EXAONE (Non-reasoning) | LG AI Research | 11.20 | — | — | — |
| 373 | Qwen3 Next 80B A3B (Reasoning) | Alibaba | 11.20 | $0.15 | $1.2 | 163 |
| 374 | GLM-4.6V (Reasoning) | Z AI | 11.20 | $0.3 | $0.9 | 88 |
| 375 | Grok 4 Fast (Non-reasoning) | SpaceXAI | 11.10 | $0.2 | $0.5 | — |
| 376 | GLM-4.5-Air | Z AI | 11.10 | $0.17 | $0.98 | 74 |
| 377 | Ling 3.0 Tiny | InclusionAI | 11.10 | $0 | $0 | 16 |
| 378 | Granite 4.2 8B | IBM | 11.10 | $0.06 | $0.25 | 118 |
| 379 | GPT-5.4 mini (Non-reasoning) | OpenAI | 11.10 | $0.75 | $4.5 | 183 |
| 380 | Nova 2.0 Omni (Low) | Amazon | 11.10 | $0.3 | $2.5 | — |
| 381 | o3-mini (High) | OpenAI | 11.00 | $1.1 | $4.4 | 187 |
| 382 | Mi:dm K 2.5 Pro | Korea Telecom | 11.00 | — | — | — |
| 383 | Ring-1T | InclusionAI | 10.90 | — | — | — |
| 384 | Mercury 2 | Inception | 10.80 | $0.25 | $0.75 | 460 |
| 385 | G9v3-3B | AI9Stars | 10.80 | $0 | $0 | — |
| 386 | Qwen3.5 4B (Non-reasoning) | Alibaba | 10.80 | $0.03 | $0.15 | 13 |
| 387 | Trinity Large Thinking | Arcee AI | 10.80 | $0.25 | $0.8 | 346 |
| 388 | INTELLECT-3 (Based on GLM-4.5-Air) | Prime Intellect | 10.60 | — | — | — |
| 389 | GLM-4.7-Flash (Non-reasoning) | Z AI | 10.60 | $0.07 | $0.4 | 118 |
| 390 | Solar Open 100B (Reasoning) | Upstage | 10.40 | — | — | — |
| 391 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 10.40 | $0.1 | $0.4 | — | |
| 392 | GPT-5 (ChatGPT) | OpenAI | 10.40 | — | — | — |
| 393 | Grok 3 Reasoning Beta | SpaceXAI | 10.40 | — | — | — |
| 394 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 10.30 | $0.3 | $0.9 | 237 |
| 395 | GPT-4.1 mini | OpenAI | 10.20 | $0.4 | $1.6 | 147 |
| 396 | gpt-oss-120b (Low) | OpenAI | 10.20 | $0.15 | $0.5 | 238 |
| 397 | gpt-oss-20b (Low) | OpenAI | 10.00 | $0.07 | $0.215 | 309 |
| 398 | MiniMax M1 40k | MiniMax | 10.00 | — | — | — |
| 399 | Nova 2.0 Pro Preview (Non-reasoning) | Amazon | 10.00 | $1.375 | $11 | 107 |
| 400 | North Mini Code | Cohere | 9.90 | $0 | $0 | 83 |
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.