Handling long prompts well. Pair this with the context-window column. Ranked by Arena text / longer_query, priced against live API rates. 45 models have a published score on this board.
Capability published 2026-10-22 · pricing retrieved 2026-10-25
google/gemini-4-argongoogle/gemini-3.8-flashdeepseek/deepseek-v4-flash-0731google/gemini-3.8-flashRows marked frontier are Pareto-optimal — nothing we track is both stronger and cheaper. "Strength" rescales the board so 100% = parity with the leader.
| # | Model | Provider | Score | Strength | $/1M | Context | Tools |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argongoogle/gemini-4-argon | 1538 | 100% | $4.00 | 1.048576M | tools | |
| 2 | Claude Opus 5.5anthropic/claude-opus-5.5 | Anthropic | 1533 | 99% | $8.00 | 1M | tools |
| 3 | Claude Fable 5.1anthropic/claude-fable-5.1 | Anthropic | 1524 | 96% | $20.00 | 1M | tools |
| 4 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 1517 | 94% | $10.00 | 1M | tools |
| 5 | Claude Fable 5anthropic/claude-fable-5 | Anthropic | 1510 | 92% | $20.00 | 1M | tools |
| 6 | Gemini 3.8 Flashgoogle/gemini-3.8-flash | 1507 | 91% | $1.66 | 1.048576M | tools | |
| 7 | Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | Anthropic | 1495 | 88% | $4.00 | 1M | tools |
| 8 | Gemini 3.7 Flashgoogle/gemini-3.7-flash | 1494 | 88% | $1.50 | 1.048576M | tools | |
| 9 | Kimi K3moonshotai/kimi-k3 | Moonshot AI | 1493 | 87% | $2.88 | 1.048576M | tools |
| 10 | Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Qwen (Alibaba) | 1489 | 86% | $3.00 | 1M | tools |
| 11 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 1484 | 85% | $10.00 | 1M | tools |
| 12 | GLM 5.3z-ai/glm-5.3 | Z.ai (Zhipu) | 1483 | 84% | $0.41 | 1.048576M | tools |
| 13 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai (Zhipu) | 1482 | 84% | $0.24 | 1.048576M | tools |
| 14 | GLM 5.2z-ai/glm-5.2 | Z.ai (Zhipu) | 1479 | 83% | $1.77 | 1.048576M | tools |
| 15 | Gemini 3.6 Flashgoogle/gemini-3.6-flash | 1475 | 82% | $1.50 | 1.048576M | tools | |
| 16 | DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek | 1474 | 82% | $0.27 | 1.048576M | tools |
| 17 | Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI | 1468 | 80% | $1.34 | 262K | tools |
| 18 | GLM 5.1z-ai/glm-5.1 | Z.ai (Zhipu) | 1467 | 80% | $2.15 | 205K | tools |
| 19 | Claude Sonnet 5anthropic/claude-sonnet-5 | Anthropic | 1462 | 79% | $4.00 | 1M | tools |
| 20 | Grok 4.5x-ai/grok-4.5 | xAI | 1462 | 79% | $3.00 | 500K | tools |
| 21 | GPT-6 Astraopenai/gpt-6-astra | OpenAI | 1462 | 79% | $20.00 | 1.05M | tools |
| 22 | GPT-6.1 Solopenai/gpt-6.1-sol | OpenAI | 1461 | 78% | $4.00 | 1.05M | tools |
| 23 | DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | DeepSeek | 1458 | 77% | $0.99 | 1.048576M | tools |
| 24 | DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek | 1458 | 77% | $0.26 | 1.048576M | tools |
| 25 | Grok 4.6x-ai/grok-4.6 | xAI | 1457 | 77% | $3.00 | 500K | tools |
Capability: Arena leaderboard dataset (CC-BY-4.0), Arena text / longer_query, published 2026-10-22. Pricing: OpenRouter, retrieved 2026-10-25. (input x 3 + output x 1) / 4.
curl -s https://agentleaderboards.com/api/v1/route/long-input.json | jq .picksNo key, open CORS, refreshed daily. Set your own budget and constraints →
Writing & editing code · Autonomous agent work · Tool-call reliability · Following operator instructions · Recovering from shell errors · Hard reasoning · Mathematics · Precise instruction following · Long multi-turn chat · Creative writing · General assistant · Software & IT services · Legal & government · Medicine & healthcare · Science · Business & finance · Writing & language