RankModel
Arrow 1.1
Official API
40.9339.0052.2035.20
Gemini 3.1 Pro
Official API. reasoning_effort: medium
33.1054.8042.2021.20
Gemini 3.5 Flash
Official API. reasoning_effort: medium
28.9547.4030.0022.60
4GPT-5.5
Cloudflare Proxy API. Reasoning_effortt: medium
22.9950.6025.4013.00
5Gemini 3 Flash
Official API. reasoning_effort: minimal
22.4941.6029.8012.40
6Qwen3.6-Max-Preview
Official API. Thinking mode enabled.
18.5328.6017.8015.80
7DeepSeek v4 Pro
Official API. Thinking mode enabled. reasoning_effort: high
16.3726.2019.4011.60
8GLM-5.1
Official API
16.3033.4018.0010.00
9MiMo-V2.5-Pro
Official API
15.6327.8017.8010.60
10Qwen3.7-Max
Official API. Thinking mode enabled.
15.4024.2016.2012.20
11Claude Sonnet 4.6
Cloudflare Proxy API. Effort: medium
14.6929.4013.8010.60
12Claude Opus 4.8
Cloudflare Proxy API. Thinking: adaptive. Effort: high
13.7326.4012.6010.40
13Doubao-Seed-2.0-pro
Official API
13.5725.4013.0010.20
14MiMo-V2.5
Official API
13.2322.809.4012.40
15Qwen3.6-Plus
Official API. Thinking mode enabled.
12.4318.8015.009.00
16DeepSeek v4 Flash
Official API. Thinking mode disabled.
11.9616.6015.008.80
17Qwen3.7-Plus
Official API. Thinking mode enabled.
11.3119.2012.808.00
18Claude Opus 4.7
Cloudflare Proxy API. Thinking: adaptive. Effort: medium
10.5919.2010.408.00
19Composer 2
Generated by Cursor Subagents
8.6113.6011.205.60
20Grok 4.3
Official API
7.5813.406.806.20
21Gemini 3.1 Flash-Lite
Official API. reasoning_effort: minimal
7.4722.406.403.40
22Hy3 preview
OpenRouter API
6.1315.008.202.20
23Composer 2.5
Generated by Cursor Subagents
5.8515.208.201.60
24Kimi K2.6
Official API. Thinking mode enabled.
5.5615.602.404.20
25Step 3.7 Flash
OpenRouter API
5.0610.405.403.20
26Step 3.5 Flash
OpenRouter API
3.179.003.801.00