Pick the job, set what you're willing to pay, and see what the measured data says. Capability comes from human preference votes on that specific kind of work; price is live API pricing. Nothing here is a blended "intelligence score" we invented.
Rows on the frontier are Pareto-optimal: nothing we track is both stronger and cheaper. "Strength vs leader" rescales the board so 100% = parity with the best model on it.
| # | Model | Provider | Score | Strength | $/1M | Context | Tools | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5anthropic/claude-opus-5.5 | Anthropic | 1545 | 100% | $8.00 | 1M | tools | frontier |
| 2 | Gemini 4 Argongoogle/gemini-4-argon | 1539 | 98% | $4.00 | 1.048576M | tools | frontier | |
| 3 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 1533 | 96% | $10.00 | 1M | tools | |
| 4 | Claude Fable 5.1anthropic/claude-fable-5.1 | Anthropic | 1531 | 96% | $20.00 | 1M | tools | |
| 5 | Claude Fable 5anthropic/claude-fable-5 | Anthropic | 1518 | 92% | $20.00 | 1M | tools | |
| 6 | Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | Anthropic | 1510 | 90% | $4.00 | 1M | tools | frontier |
| 7 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai (Zhipu) | 1508 | 89% | $0.24 | 1.048576M | tools | frontier |
| 8 | Kimi K3moonshotai/kimi-k3 | Moonshot AI | 1508 | 89% | $2.88 | 1.048576M | tools | |
| 9 | Gemini 3.8 Flashgoogle/gemini-3.8-flash | 1508 | 89% | $1.66 | 1.048576M | tools | ||
| 10 | Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Qwen (Alibaba) | 1503 | 88% | $3.00 | 1M | tools | |
| 11 | DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek | 1501 | 88% | $0.27 | 1.048576M | tools | |
| 12 | Gemini 3.7 Flashgoogle/gemini-3.7-flash | 1501 | 87% | $1.50 | 1.048576M | tools | ||
| 13 | GLM 5.3z-ai/glm-5.3 | Z.ai (Zhipu) | 1498 | 86% | $0.41 | 1.048576M | tools | |
| 14 | Gemini 3.6 Flashgoogle/gemini-3.6-flash | 1491 | 85% | $1.50 | 1.048576M | tools | ||
| 15 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 1491 | 84% | $10.00 | 1M | tools | |
| 16 | GPT-6 Astraopenai/gpt-6-astra | OpenAI | 1489 | 84% | $20.00 | 1.05M | tools | |
| 17 | Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI | 1488 | 84% | $1.34 | 262K | tools | |
| 18 | GLM 5.2z-ai/glm-5.2 | Z.ai (Zhipu) | 1487 | 83% | $1.77 | 1.048576M | tools | |
| 19 | GLM 5.1z-ai/glm-5.1 | Z.ai (Zhipu) | 1486 | 83% | $2.15 | 205K | tools | |
| 20 | Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI | 1484 | 83% | $1.00 | 262K | tools | |
| 21 | Claude Sonnet 5anthropic/claude-sonnet-5 | Anthropic | 1483 | 82% | $4.00 | 1M | tools | |
| 22 | Qwen3.8 27Bqwen/qwen3.8-27b | Qwen (Alibaba) | 1483 | 82% | $0.78 | 1M | tools | |
| 23 | GPT-6.1 Solopenai/gpt-6.1-sol | OpenAI | 1482 | 82% | $4.00 | 1.05M | tools | |
| 24 | Grok 4.5x-ai/grok-4.5 | xAI | 1474 | 80% | $3.00 | 500K | tools | |
| 25 | Qwen3.7 Plusqwen/qwen3.7-plus | Qwen (Alibaba) | 1473 | 80% | $0.56 | 1M | tools | |
| 26 | MiniMax M3minimax/minimax-m3 | MiniMax | 1470 | 79% | $0.53 | 1.048576M | tools | |
| 27 | DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | DeepSeek | 1469 | 79% | $0.99 | 1.048576M | tools | |
| 28 | DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek | 1469 | 79% | $0.26 | 1.048576M | tools | |
| 29 | GLM 5V Turboz-ai/glm-5v-turbo | Z.ai (Zhipu) | 1467 | 78% | $1.90 | 203K | tools | |
| 30 | Grok 4.6x-ai/grok-4.6 | xAI | 1465 | 77% | $3.00 | 500K | tools | |
| 31 | Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral | 1461 | 76% | $3.00 | 262K | tools | |
| 32 | Grok 4.20x-ai/grok-4.20 | xAI | 1459 | 76% | $1.56 | 2M | tools | |
| 33 | Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent | xAI | 1457 | 75% | $1.56 | 2M | — | |
| 34 | DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | DeepSeek | 1457 | 75% | $0.07 | 1.048576M | tools | frontier |
| 35 | DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek | 1457 | 75% | $0.11 | 1.048576M | tools | |
| 36 | MiniMax M2.7minimax/minimax-m2.7 | MiniMax | 1454 | 74% | $0.53 | 205K | tools | |
| 37 | Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 1453 | 74% | $0.85 | 1.048576M | tools | ||
| 38 | Claude Haiku 5.5anthropic/claude-haiku-5.5 | Anthropic | 1450 | 73% | $0.20 | 1M | tools | |
| 39 | GPT-6 Solopenai/gpt-6-sol | OpenAI | 1448 | 73% | $4.00 | 1.05M | tools | |
| 40 | GPT-6 Lunaopenai/gpt-6-luna | OpenAI | 1438 | 70% | $0.20 | 1.05M | tools | |
| 41 | Grok 4.7x-ai/grok-4.7 | xAI | 1427 | 67% | $3.00 | 500K | tools | |
| 42 | MiniMax M2.1minimax/minimax-m2.1 | MiniMax | 1421 | 66% | $0.53 | 205K | tools | |
| 43 | Grok 4.3x-ai/grok-4.3 | xAI | 1414 | 64% | $1.56 | 1M | tools | |
| 44 | MiniMax M2.5minimax/minimax-m2.5 | MiniMax | 1380 | 56% | $0.53 | 205K | tools | |
| 45 | Ministral 3 8B 2512mistralai/ministral-8b-2512 | Mistral | 1202 | 24% | $0.15 | 262K | tools |
Capability: Arena leaderboard dataset (CC-BY-4.0), published 2026-10-22. Pricing: OpenRouter, retrieved 2026-10-25. Blended price = (input×3 + output×1) ÷ 4.
GET /api/v1/route/{task}.json, or /api/v1/route/all.json for every task at once. No key, open CORS. See API & Bots.