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 · 401–450
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 401 | Qwen2.5 Max | Alibaba | 10.10 | — | — | — |
| 402 | Gemini 1.5 Pro (Sep '24) | 9.90 | — | — | — | |
| 403 | Solar Pro 2 (Preview) (Non-reasoning) | Upstage | 9.90 | — | — | — |
| 404 | Qwen3 VL 30B A3B Instruct | Alibaba | 9.90 | $0.2 | $0.8 | 111 |
| 405 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 9.90 | $0.13 | $0.4 | 85 |
| 406 | Claude 3.5 Sonnet (Oct '24) | Anthropic | 9.80 | $3 | $15 | — |
| 407 | DeepSeek R1 Distill Llama 70B | DeepSeek | 9.80 | $0.7 | $1.1 | 27 |
| 408 | DeepSeek R1 Distill Qwen 14B | DeepSeek | 9.70 | — | — | — |
| 409 | Falcon-H1R-7B | TII UAE | 9.70 | — | — | — |
| 410 | GPT-4.1 nano | OpenAI | 9.60 | $0.1 | $0.4 | 128 |
| 411 | Ling-flash-2.0 | InclusionAI | 9.60 | $0.14 | $0.57 | 53 |
| 412 | Gemma 4 E2B (Reasoning) | 9.50 | — | — | — | |
| 413 | Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 9.50 | $0.25 | $0.97 | 101 |
| 414 | Sonar | Perplexity | 9.40 | — | — | — |
| 415 | GPT-4o (Aug '24) | OpenAI | 9.40 | $2.5 | $10 | 81 |
| 416 | Qwen2.5 Instruct 72B | Alibaba | 9.40 | $0.47 | $0.49 | — |
| 417 | Llama 3.3 Instruct 70B | Meta | 9.30 | $0.66 | $0.72 | 86 |
| 418 | Step3 VL 10B | StepFun | 9.30 | — | — | — |
| 419 | Qwen3 30B A3B (Reasoning) | Alibaba | 9.20 | $0.2 | $2.4 | 101 |
| 420 | Sonar Pro | Perplexity | 9.10 | — | — | — |
| 421 | QwQ 32B-Preview | Alibaba | 9.10 | — | — | — |
| 422 | Devstral Small (Jul '25) | Mistral | 9.10 | — | — | — |
| 423 | GLM-4.5V (Reasoning) | Z AI | 9.00 | $0.6 | $1.8 | 78 |
| 424 | Mistral Large 2 (Nov '24) | Mistral | 9.00 | — | — | — |
| 425 | Ministral 3 8B | Mistral | 9.00 | $0.15 | $0.15 | 123 |
| 426 | Qwen3 30B A3B 2507 Instruct | Alibaba | 8.90 | $0.2 | $0.8 | 133 |
| 427 | ERNIE 4.5 300B A47B | Baidu | 8.90 | $0.28 | $1.1 | — |
| 428 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 8.90 | $0.6 | $1.8 | 52 |
| 429 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA | 8.80 | $0.2 | $0.6 | 73 |
| 430 | Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 8.80 | $1 | $3 | 32 |
| 431 | Solar Pro 2 (Reasoning) | Upstage | 8.80 | — | — | — |
| 432 | Gemma 4 E4B (Non-reasoning) | 8.70 | $0.02 | $0.1 | 57 | |
| 433 | Granite 4.1 30B | IBM | 8.70 | — | — | — |
| 434 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 8.70 | $0.04 | $0.16 | 204 |
| 435 | Gemini 2.0 Flash-Lite (Feb '25) | 8.60 | — | — | — | |
| 436 | NVIDIA Nemotron 3 Nano 4B | NVIDIA | 8.60 | — | — | — |
| 437 | Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 8.60 | $1 | $3 | 33 |
| 438 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | 8.50 | $0.4 | $0.4 | 42 |
| 439 | Qwen3 32B (Non-reasoning) | Alibaba | 8.50 | $0.16 | $0.64 | 107 |
| 440 | Gemini 2.0 Flash-Lite (Preview) | 8.40 | — | — | — | |
| 441 | Kimi Linear 48B A3B Instruct | Kimi | 8.40 | — | — | — |
| 442 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 8.40 | — | — | — |
| 443 | K2-V2 (low) | MBZUAI Institute of Foundation Models | 8.40 | — | — | — |
| 444 | GPT-4o (May '24) | OpenAI | 8.40 | $5 | $15 | 90 |
| 445 | Llama 3.1 Instruct 405B | Meta | 8.30 | — | — | — |
| 446 | Qwen3 8B (Reasoning) | Alibaba | 8.30 | $0.18 | $2.1 | 39 |
| 447 | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | NVIDIA | 8.30 | — | — | — |
| 448 | Qwen3 4B (Reasoning) | Alibaba | 8.20 | — | — | — |
| 449 | Qwen3 VL 8B Instruct | Alibaba | 8.20 | $0.18 | $0.7 | 111 |
| 450 | Claude 3.5 Sonnet (June '24) | Anthropic | 8.10 | $3 | $15 | — |
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.