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 · 501–550
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 501 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 7.50 | — | — | — |
| 502 | Solar Pro 2 (Reasoning) | Upstage | 7.50 | — | — | — |
| 503 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 7.40 | — | — | — |
| 504 | Gemini 2.0 Flash-Lite (Feb '25) | 7.40 | — | — | — | |
| 505 | Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 7.40 | $1 | $3 | 38 |
| 506 | Granite 4.1 30B | IBM | 7.40 | — | — | — |
| 507 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 7.40 | $0.04 | $0.16 | 207 |
| 508 | Qwen3 VL 8B Instruct | Alibaba | 7.30 | — | — | — |
| 509 | Gemini 2.0 Flash-Lite (Preview) | 7.30 | — | — | — | |
| 510 | Llama 3.1 Instruct 405B | Meta | 7.30 | — | — | — |
| 511 | Kimi Linear 48B A3B Instruct | Kimi | 7.30 | — | — | — |
| 512 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 7.30 | — | — | — |
| 513 | Qwen3 32B (Non-reasoning) | Alibaba | 7.30 | $0.15 | $0.6 | 53 |
| 514 | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | NVIDIA | 7.30 | — | — | — |
| 515 | K2-V2 (Low) | Institute of Foundation Models | 7.30 | — | — | — |
| 516 | GPT-4o (May '24) | OpenAI | 7.30 | $5 | $15 | 137 |
| 517 | Qwen3 4B (Reasoning) | Alibaba | 7.20 | — | — | — |
| 518 | Ring-flash-2.0 | InclusionAI | 7.20 | $0.14 | $0.57 | — |
| 519 | Claude 3.5 Sonnet (June '24) | Anthropic | 7.20 | $3 | $15 | — |
| 520 | Qwen3 32B (Reasoning) | Alibaba | 7.20 | $0.24 | $0.54 | 27 |
| 521 | GPT-4o (ChatGPT) | OpenAI | 7.20 | — | — | — |
| 522 | LFM2.5-8B-A1B | Liquid AI | 7.20 | — | — | — |
| 523 | Llama 3.1 Tulu3 405B | Allen Institute for AI | 7.20 | — | — | — |
| 524 | GPT-5 nano (Minimal) | OpenAI | 7.10 | $0.05 | $0.4 | 143 |
| 525 | Mistral Small 3.1 | Mistral | 7.10 | $0.08 | $0.135 | 29 |
| 526 | Grok 2 (Dec '24) | SpaceXAI | 7.10 | — | — | — |
| 527 | Olmo 3.1 32B Think | Allen Institute for AI | 7.10 | $0 | $0 | — |
| 528 | Gemini 1.5 Flash (Sep '24) | 7.10 | — | — | — | |
| 529 | Pixtral Large | Mistral | 7.10 | — | — | — |
| 530 | Command A | Cohere | 7.00 | $2.5 | $10 | 61 |
| 531 | Mistral Small 3.2 | Mistral | 7.00 | $0.075 | $0.2 | 36 |
| 532 | Solar Pro 2 (Non-reasoning) | Upstage | 7.00 | — | — | — |
| 533 | Nova Pro | Amazon | 7.00 | $0.8 | $3.2 | 127 |
| 534 | GPT-4 Turbo | OpenAI | 7.00 | $10 | $30 | 32 |
| 535 | Qwen3 VL 4B (Reasoning) | Alibaba | 7.00 | — | — | — |
| 536 | Qwen2.5 Instruct 32B | Alibaba | 6.90 | — | — | — |
| 537 | Qwen3.5 2B (Reasoning) | Alibaba | 6.90 | — | — | — |
| 538 | Llama 3.1 Nemotron Instruct 70B | NVIDIA | 6.90 | — | — | — |
| 539 | Llama 3.1 Instruct 8B | Meta | 6.90 | $0.035 | $0.065 | 139 |
| 540 | Grok Beta | SpaceXAI | 6.90 | — | — | — |
| 541 | Mistral Large 2 (Jul '24) | Mistral | 6.80 | $2 | $6 | — |
| 542 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | 6.80 | $0.05 | $0.2 | 248 |
| 543 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | 6.80 | $0.05 | $0.195 | 171 |
| 544 | GLM-4.5V (Non-reasoning) | Z AI | 6.70 | $0.6 | $1.8 | 45 |
| 545 | Qwen2.5 Coder Instruct 32B | Alibaba | 6.70 | — | — | — |
| 546 | Gemini 2.5 Flash-Lite (Non-reasoning) | 6.70 | $0.1 | $0.4 | 287 | |
| 547 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 6.70 | — | — | — |
| 548 | Nova Lite | Amazon | 6.70 | $0.06 | $0.24 | 169 |
| 549 | GPT-4 | OpenAI | 6.70 | $30 | $60 | — |
| 550 | Qwen3 4B 2507 Instruct | Alibaba | 6.70 | — | — | — |
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.