Zed最佳AI模型
Zed is a high-performance code editor with built-in AI assistant support. It connects to multiple model providers for inline completions and chat.
Zed的重要因素
Best Models for Zed
Top 15 by tool-optimized score
Zed全部模型排名（378个模型）
Scored by: benchmark performance (90%) from MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations, with capabilities and context as tiebreakers (10%).
| # | 模型 | 评分 | 输出$/百万 |
|---|---|---|---|
| 1 | Qwen3.8 Max Arena Elo: 1497 | 87 | $6.00 |
| 2 | Gemini 3.6 Flash Arena Elo: 1485 | 86 | $7.50 |
| 3 | Muse Spark 1.1 Arena Elo: 1487 | 86 | $4.25 |
| 4 | Claude Fable 5 (batch) | 86 | $25.00 |
| 5 | Gemini 3.5 Flash Arena Elo: 1477 | 86 | $9.00 |
| 6 | Claude Opus 5 (Fast) | 85 | $50.00 |
| 7 | Claude Opus 5 | 85 | $25.00 |
| 8 | Grok 4.5 Arena Elo: 1468 | 85 | $6.00 |
| 9 | Claude Fable 5 SWE-bench: 95% | 85 | $50.00 |
| 10 | Claude Opus 4.8 (Fast) | 85 | $50.00 |
| 11 | Claude Opus 4.8 (batch) | 85 | $12.50 |
| 12 | Claude Opus 4.7 (Fast) | 85 | $150.00 |
| 13 | MiMo-V2.5-Pro Arena Elo: 1467 | 85 | $0.870 |
| 14 | Claude Opus 4.7 (batch) | 85 | $12.50 |
| 15 | GLM 5.1 Arena Elo: 1468 | 85 | $2.99 |
| 16 | Gemini 3.5 Flash Lite Arena Elo: 1459 | 84 | $2.50 |
| 17 | Hy3 Arena Elo: 1453 | 84 | $0.528 |
| 18 | Qwen3.7 Plus Arena Elo: 1458 | 84 | $1.28 |
| 19 | Qwen3.6 Max Preview Arena Elo: 1460 | 84 | $6.16 |
| 20 | GPT-5.5 Pro (batch) | 84 | $90.00 |
| 21 | GPT-5.5 (batch) | 84 | $15.00 |
| 22 | Kimi K2.6 Arena Elo: 1461 | 84 | $2.44 |
| 23 | Gemini 3.1 Pro Preview Custom Tools | 84 | $12.00 |
| 24 | Gemini 3.1 Pro Preview (batch) | 84 | $6.00 |
| 25 | GLM 5 Arena Elo: 1457 | 84 | $2.55 |
| 26 | Inkling Arena Elo: 1442 | 83 | $4.05 |
| 27 | MiniMax M3 Arena Elo: 1445 | 83 | $1.20 |
| 28 | Gemma 4 31B Arena Elo: 1451 | 83 | $0.340 |
| 29 | Qwen3.6 Plus Arena Elo: 1443 | 83 | $1.95 |
| 30 | GPT-5.4 Pro | 83 | $180.00 |
| 31 | GPT-5.4 Pro (batch) | 83 | $90.00 |
| 32 | GPT-5.4 (batch) | 83 | $7.50 |
| 33 | GPT-5.3-Codex | 83 | $14.00 |
| 34 | Qwen3.5 397B A17B Arena Elo: 1442 | 83 | $2.34 |
| 35 | Claude Opus 4.6 (batch) | 83 | $12.50 |
| 36 | GPT-5.2-Codex | 83 | $14.00 |
| 37 | GLM 4.7 Arena Elo: 1442 | 83 | $1.75 |
| 38 | GPT-5.2 Pro | 83 | $168.00 |
| 39 | GPT-5.2 Pro (batch) | 83 | $84.00 |
| 40 | GPT-5.2 (batch) | 83 | $7.00 |
| 41 | Claude Opus 4.1 Arena Elo: 1449 | 83 | $75.00 |
| 42 | Inkling Small Arena Elo: 1431 | 82 | $1.20 |
| 43 | GPT-5.6 Luna Pro | 82 | $0.600 |
| 44 | GPT-5.6 Luna Pro (batch) | 82 | $0.600 |
| 45 | GPT-5.6 Luna | 82 | $0.600 |
| 46 | GPT-5.6 Luna (batch) | 82 | $0.600 |
| 47 | GPT-5.6 Terra Pro | 82 | $6.00 |
| 48 | GPT-5.6 Terra Pro (batch) | 82 | $6.00 |
| 49 | GPT-5.6 Terra | 82 | $6.00 |
| 50 | GPT-5.6 Terra (batch) | 82 | $6.00 |
更多工具排名
Based on our analysis of coding benchmarks, capability matching, and pricing, Qwen3.8 Max currently ranks #1 for Zed. Rankings are rebuilt as benchmark, pricing, and provider data refresh.
We score models using benchmark performance (90%) from LMArena, HumanEval, SWE-bench, MMLU, and 15+ standardized evaluations. Capabilities and context serve as tiebreakers (10%). Only models with the capabilities Zed needs are included in the tool-specific rankings.
We currently track 378 AI models compatible with Zed. This includes models from OpenAI, Anthropic, Google, DeepSeek, and other providers accessible via API.
Many open-source models are compatible with Zed through API providers like OpenRouter, Together AI, and Groq. Check our rankings to see which open-source models perform best.
Rankings refresh whenever the underlying benchmark, pricing, and catalog sources refresh. That means some signals update faster than others, and the page reflects the latest verified source data available.