| 1 |
Claude Opus 4.8
anthropic/claude-opus-4.8
|
2026-05-27 |
verbosity: max |
Yes
|
1322 |
9 |
9-0 |
100% |
66.0 |
| 2 |
GPT-5.5
openai/gpt-5.5
|
2026-04-24 |
reasoning: xhigh |
Yes
|
1265 |
11 |
10-1 |
91% |
6.0 |
| 3 |
GPT-5.4 Pro
openai/gpt-5.4-pro
|
2026-03-05 |
reasoning: xhigh |
Yes
|
1264 |
12 |
8-4 |
67% |
10.0 |
| 4 |
Gemini 3.5 Flash
google/gemini-3.5-flash
|
2026-05-19 |
reasoning: high |
Yes
|
1263 |
8 |
6-2 |
75% |
21.0 |
| 5 |
GPT-5.4
openai/gpt-5.4
|
2026-03-05 |
reasoning: xhigh |
Yes
|
1259 |
12 |
8-4 |
67% |
10.0 |
| 6 |
GLM 5.2
z-ai/glm-5.2
|
2026-06-16 |
reasoning: xhigh |
No
|
1256 |
12 |
8-4 |
67% |
40.0 |
| 7 |
Qwen3.7 Plus
qwen/qwen3.7-plus
|
2026-06-03 |
custom |
Yes
|
1231 |
10 |
6-4 |
60% |
7.0 |
| 8 |
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
|
2026-06-12 |
custom |
Yes
|
1215 |
11 |
6-5 |
55% |
13.0 |
| 9 |
Qwen3.7 Max
qwen/qwen3.7-max
|
2026-05-21 |
custom |
No
|
1214 |
3 |
2-1 |
67% |
8.0 |
| 10 |
GPT-5.5 Pro
openai/gpt-5.5-pro
|
2026-04-24 |
reasoning: xhigh |
Yes
|
1213 |
17 |
9-8 |
53% |
35.0 |
| 11 |
Grok 4.3
x-ai/grok-4.3
|
2026-04-30 |
reasoning: high |
Yes
|
1202 |
10 |
5-5 |
50% |
9.0 |
| 12 |
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
|
2026-04-24 |
reasoning: xhigh |
No
|
1200 |
10 |
5-5 |
50% |
18.0 |
| 13 |
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
|
2026-02-19 |
reasoning: high |
Yes
|
1184 |
11 |
5-6 |
45% |
4.0 |
| 14 |
Claude Haiku 4.5
anthropic/claude-haiku-4.5
|
2025-10-15 |
custom |
Yes
|
1153 |
23 |
8-15 |
35% |
4.0 |
| 15 |
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
|
2026-02-17 |
verbosity: max |
Yes
|
1153 |
3 |
0-3 |
0% |
11.0 |
| 16 |
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
|
2026-04-24 |
reasoning: xhigh |
No
|
1152 |
9 |
3-6 |
33% |
8.0 |
| 17 |
Claude Opus 4.5
anthropic/claude-opus-4.5
|
2025-11-24 |
verbosity: max |
Yes
|
1135 |
10 |
3-7 |
30% |
8.0 |
| 18 |
GPT OSS 120B
openai/gpt-oss-120b
|
2025-08-05 |
reasoning: high |
No
|
1123 |
12 |
3-9 |
25% |
9.0 |
| 19 |
GPT OSS 20B
openai/gpt-oss-20b
|
2025-08-05 |
reasoning: high |
No
|
1093 |
10 |
1-9 |
10% |
7.0 |
| 20 |
Mistral Medium 3.5
mistralai/mistral-medium-3-5
|
2026-04-30 |
reasoning: high |
Yes
|
1086 |
9 |
1-8 |
11% |
25.0 |