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 · 601–611
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 601 | LFM2.5-VL-1.6B | Liquid AI | 1.00 | $0 | $0 | 342 |
| 602 | Qwen3 0.6B (Reasoning) | Alibaba | 1.00 | — | — | — |
| 603 | Granite 4.0 350M | IBM | 1.00 | — | — | — |
| 604 | Llama 3.2 Instruct 1B | Meta | 1.00 | — | — | — |
| 605 | Tiny Aya Global | Cohere | 1.00 | $0 | $0 | — |
| 606 | Llama 3 Instruct 8B | Meta | 1.00 | $0.04 | $0.14 | — |
| 607 | Apertus 8B Instruct | Swiss AI Initiative | 1.00 | $0.1 | $0.2 | — |
| 608 | Granite 4.0 H 350M | IBM | 1.00 | — | — | — |
| 609 | Gemma 3n E4B Instruct | 1.00 | $0.06 | $0.12 | 59 | |
| 610 | Gemma 3n E2B Instruct | 1.00 | $0 | $0 | — | |
| 611 | Gemma 3 1B Instruct | 1.00 | $0 | $0 | — |
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.