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 · 551–600
| # | Model | Creator | Intelligence | $/1M in | $/1M out | tok/s |
|---|---|---|---|---|---|---|
| 551 | GPT-4o mini | OpenAI | 6.70 | $0.15 | $0.6 | 111 |
| 552 | Mistral Small 3 | Mistral | 6.70 | $0.05 | $0.08 | 58 |
| 553 | Qwen3 14B (Non-reasoning) | Alibaba | 6.70 | $0.12 | $0.24 | 28 |
| 554 | Llama 3.1 Instruct 70B | Meta | 6.60 | $0.56 | $0.56 | 36 |
| 555 | Sarvam 30B (High) | Sarvam | 6.60 | $0.026 | $0.11 | — |
| 556 | Granite 4.1 8B | IBM | 6.60 | — | — | — |
| 557 | DeepSeek-V2.5 | DeepSeek | 6.60 | — | — | — |
| 558 | DeepSeek-V2.5 (Dec '24) | DeepSeek | 6.60 | — | — | — |
| 559 | Gemini 2.0 Flash Thinking Experimental (Dec '24) | 6.60 | — | — | — | |
| 560 | Qwen3 4B (Non-reasoning) | Alibaba | 6.60 | — | — | — |
| 561 | Qwen3 30B A3B (Non-reasoning) | Alibaba | 6.60 | $0.12 | $0.5 | 99 |
| 562 | DeepSeek R1 Distill Llama 8B | DeepSeek | 6.50 | — | — | — |
| 563 | Gemma 4 E2B (Non-reasoning) | 6.50 | — | — | — | |
| 564 | Mistral Saba | Mistral | 6.50 | — | — | — |
| 565 | Olmo 3.1 32B Instruct | Allen Institute for AI | 6.50 | — | — | — |
| 566 | Llama 4 Scout | Meta | 6.50 | $0.18 | $0.66 | 80 |
| 567 | Olmo 3 32B Think | Allen Institute for AI | 6.50 | — | — | — |
| 568 | Gemini 1.5 Pro (May '24) | 6.40 | — | — | — | |
| 569 | Qwen2.5 Turbo | Alibaba | 6.40 | $0.05 | $0.2 | 85 |
| 570 | Qwen3 14B (Reasoning) | Alibaba | 6.40 | $0.12 | $0.24 | 26 |
| 571 | R1 1776 | Perplexity | 6.40 | — | — | — |
| 572 | Llama 3.2 Instruct 90B (Vision) | Meta | 6.40 | — | — | — |
| 573 | Reka Flash (Sep '24) | Reka AI | 6.40 | $0.2 | $0.8 | — |
| 574 | Solar Mini | Upstage | 6.40 | $0.15 | $0.15 | — |
| 575 | EXAONE 4.0 32B (Non-reasoning) | LG AI Research | 6.30 | — | — | — |
| 576 | Grok-1 | SpaceXAI | 6.30 | — | — | — |
| 577 | Qwen2 Instruct 72B | Alibaba | 6.30 | — | — | — |
| 578 | Celeris-1 | Celeris | 6.30 | $0.2 | $0.7 | 1459 |
| 579 | Phi-4 Mini Instruct | Microsoft | 6.30 | $0.075 | $0.3 | 46 |
| 580 | Qwen3.5 2B (Non-reasoning) | Alibaba | 6.20 | — | — | — |
| 581 | Gemini 1.5 Flash-8B | 6.20 | — | — | — | |
| 582 | Jamba 1.7 Large | AI21 Labs | 6.10 | — | — | — |
| 583 | Qwen3.5 0.8B (Reasoning) | Alibaba | 6.10 | — | — | — |
| 584 | DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 6.10 | — | — | — |
| 585 | Qwen3 Omni 30B A3B Instruct | Alibaba | 6.00 | $0.25 | $0.97 | 96 |
| 586 | Hermes 3 - Llama-3.1 70B | Nous Research | 6.00 | $0.7 | $0.7 | 31 |
| 587 | OLMo 2 32B | Allen Institute for AI | 6.00 | — | — | — |
| 588 | Granite 4.0 H Small | IBM | 6.00 | $0.06 | $0.25 | 14 |
| 589 | Ministral 3 14B | Mistral | 6.00 | $0.2 | $0.2 | 68 |
| 590 | DeepSeek-Coder-V2 | DeepSeek | 6.00 | — | — | — |
| 591 | Jamba 1.6 Large | AI21 Labs | 6.00 | — | — | — |
| 592 | Qwen3 8B (Non-reasoning) | Alibaba | 6.00 | $0.2 | $0.2 | — |
| 593 | Jamba 1.5 Large | AI21 Labs | 6.00 | $2 | $8 | — |
| 594 | Nova Micro | Amazon | 5.90 | $0.035 | $0.14 | 318 |
| 595 | Granite 4.1 3B | IBM | 5.90 | — | — | — |
| 596 | Gemini 1.5 Flash (May '24) | 5.90 | — | — | — | |
| 597 | Claude 3 Sonnet | Anthropic | 5.90 | — | — | — |
| 598 | Phi-4 | Microsoft | 5.90 | $0.125 | $0.5 | 41 |
| 599 | LFM2 24B A2B | Liquid AI | 5.90 | — | — | — |
| 600 | Gemini 1.0 Ultra | 5.80 | — | — | — |
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.