Best AI Reasoning Models
19 models — live arena Elo, API pricing, downloads, and our news-mention tracking. Synced daily. JSON is available at /api/models.
All uses💬 Chat 366🖼️ Image 63💻 Code 26🎬 Video 25🔍 Search 25🧮 Reasoning 19👁️ Vision 14🎙️ Audio 4🛡️ Safety 2
All orgsopenai 91qwen 54google 51anthropic 31mistralai 21deepseek 19z-ai 18xai 13nvidia 12meta-llama 10minimax 10meta 9
🏆 Best right now
R1 0528
deepseek · Elo 1428
💸 Best value
Qwen3 Next 80B A3B Thinking
qwen · Elo 1368 at $0.15/M
🔓 Open-weight pick
R1
deepseek · Elo 1373
| # | Model | Use | Arena Elo | In / Out $/M | Context | HF DLs | 7d News | Released |
|---|---|---|---|---|---|---|---|---|
| 1 | R1 0528deepseek | 🧮 Reasoning | 1428 | $0.50 / $2.15 | 164K | 172.4K | — | 17mo |
| 2 | Qwen3 235B A22B Thinking 2507qwen | 🧮 Reasoning | 1415 | $0.45 / $3.50 | 262K | 17.5K | — | 15mo |
| 3 | Qwen3 VL 235B A22B Thinkingqwen | 🧮 Reasoning | 1400 | $0.40 / $4.00 | 131K | 21.1K | — | 13mo |
| 4 | R1deepseekopen | 🧮 Reasoning | 1373 | $0.70 / $2.50 | 164K | 1.4M | — | 21mo |
| 5 | Qwen3 Next 80B A3B Thinkingqwen | 🧮 Reasoning | 1368 | $0.15 / $1.20 | 262K | 39.6K | — | 13mo |
| 6 | Trinity Large Thinkingarcee-ai | 🧮 Reasoning | 1340 | $0.25 / $0.80 | 262K | 2.3K | — | 6mo |
| 7 | Olmo 3 32B Thinkallenai | 🧮 Reasoning | 1300 | $0.15 / $0.50 | 66K | 14.5K | — | 11mo |
| 8 | o1-proopenai | 🧮 Reasoning | — | $150.00 / $600.00 | 200K | — | — | 19mo |
| 9 | o3openai | 🧮 Reasoning | — | $2.00 / $8.00 | 200K | — | — | 22mo |
| 10 | o1openai | 🧮 Reasoning | — | $15.00 / $60.00 | 200K | — | — | 22mo |
| 11 | Qwen3 30B A3B Thinking 2507qwen | 🧮 Reasoning | — | $0.20 / $2.40 | 131K | 53.7K | — | 13mo |
| 12 | R1 Distill Llama 70Bdeepseekopen | 🧮 Reasoning | — | $0.80 / $0.80 | 128K | 41.8K | — | 21mo |
| 13 | o3 Proopenai | 🧮 Reasoning | — | $20.00 / $80.00 | 200K | — | — | 16mo |
| 14 | Qwen3 Max Thinkingqwen | 🧮 Reasoning | — | $0.78 / $3.90 | 262K | — | — | 9mo |
| 15 | Qwen3 VL 8B Thinkingqwen | 🧮 Reasoning | — | $0.18 / $2.10 | 256K | 108.5K | — | 12mo |
| 16 | Kimi K2 Thinkingmoonshotaiopen | 🧮 Reasoning | — | $0.60 / $2.50 | 262K | 49.5K | 1 | 11mo |
| 17 | Qwen3 VL 30B A3B Thinkingqwen | 🧮 Reasoning | — | $0.29 / $1.00 | 131K | 17.3K | — | 12mo |
| 18 | LFM2.5-1.2B-Thinking (free)liquid | 🧮 Reasoning | — | — / — | 33K | 7.8K | — | 9mo |
| 19 | Qwen Plus 0728 (thinking)qwen | 🧮 Reasoning | — | $0.26 / $0.78 | 1.0M | — | — | 13mo |
Elo: LMArena per-category arenas (CC-BY) — image/video/search models are ranked by their own arena, not text. Pricing: OpenRouter/LiteLLM. Use-case labels are auto-classified — suggest fixes on any model page. Methodology.