Skip to content

Cursor最佳AI模型

AI-Native IDE

Cursor is an AI-native code editor built on VS Code. It uses AI models for code generation, editing, and chat. Models need strong code generation, reliable instruction-following, and fast response times for interactive editing.

Last updated: 44m ago
#1
Muse Spark 1.1
meta
工具评分
87
输出$/百万
$4.25
Arena Elo
1493
#2
Gemini 3.5 Flash
Google
工具评分
86
输出$/百万
$9.00
Arena Elo
1477
#3
Claude Opus 5.5
Anthropic
工具评分
85
输出$/百万
$20.00

Cursor的重要因素

Function CallingStreamingJSON Mode大上下文强编程能力

Best Models for Cursor

Top 15 by tool-optimized score

LMMarketCap.com

Cursor全部模型排名(435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
1Muse Spark 1.1
Arena Elo: 1493
87$4.25
2Gemini 3.5 Flash
Arena Elo: 1477
86$9.00
3Claude Opus 5.585$20.00
4Claude Fable 5.185$50.00
5Claude Fable 5.1 (batch)85$25.00
6GLM 5.3 Flash
Arena Elo: 1475
85$0.500
7Claude Opus 585$25.00
8Grok 4.5
Arena Elo: 1468
85$6.00
9Claude Fable 5
SWE-bench: 95%
85$50.00
10Claude Fable 5 (batch)85$25.00
11Claude Opus 4.8 (batch)85$12.50
12MiMo-V2.5-Pro
Arena Elo: 1467
85$0.870
13Claude Opus 4.7 (batch)85$12.50
14GLM 5.1
Arena Elo: 1466
85$3.04
15Gemini 3.5 Flash Lite
Arena Elo: 1456
84$2.50
16Hy3
Arena Elo: 1456
84$0.330
17Qwen3.7 Plus
Arena Elo: 1456
84$1.28
18Qwen3.6 Max Preview
Arena Elo: 1460
84$6.16
19GPT-5.5 Pro (batch)84$90.00
20GPT-5.5 (batch)84$15.00
21Kimi K2.6
Arena Elo: 1460
84$4.00
22Gemini 3.1 Pro Preview Custom Tools84$12.00
23Gemini 3.1 Pro Preview (batch)84$6.00
24GLM 5
Arena Elo: 1458
84$1.92
25MiniMax M3
Arena Elo: 1441
83$1.20
26Gemma 4 31B
Arena Elo: 1451
83$0.340
27Qwen3.6 Plus
Arena Elo: 1443
83$1.95
28GPT-5.4 Pro83$180.00
29GPT-5.4 Pro (batch)83$90.00
30GPT-5.4 (batch)83$7.50
31GPT-5.3-Codex83$14.00
32Qwen3.5 397B A17B
Arena Elo: 1442
83$3.50
33Claude Opus 4.6 (batch)83$12.50
34GPT-5.2-Codex83$14.00
35GLM 4.7
Arena Elo: 1442
83$1.75
36GPT-5.2 Pro83$168.00
37GPT-5.2 Pro (batch)83$84.00
38GPT-5.2 (batch)83$7.00
39Grok 4.782$4.80
40Qwen3.8 27B
Arena Elo: 1437
82$3.00
41Grok 4.682$6.00
42GPT-5.6 Luna Pro82$1.20
43GPT-5.6 Luna Pro (batch)82$0.600
44GPT-5.6 Luna82$1.20
45GPT-5.6 Luna (batch)82$0.600
46GPT-5.6 Terra Pro82$12.00
47GPT-5.6 Terra Pro (batch)82$6.00
48GPT-5.6 Terra82$12.00
49GPT-5.6 Terra (batch)82$6.00
50GPT-5.6 Sol Pro82$10.00
Frequently Asked Questions

Based on our analysis of coding benchmarks, capability matching, and pricing, Muse Spark 1.1 currently ranks #1 for Cursor. 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 Cursor needs are included in the tool-specific rankings.

We currently track 435 AI models compatible with Cursor. This includes models from OpenAI, Anthropic, Google, DeepSeek, and other providers accessible via API.

Many open-source models are compatible with Cursor 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.

Best AI Models for Cursor - 2026 Rankings | LM Market Cap