Skip to main content
AITier
Home
Rankings
Models
Providers
Widgets
Test
EN
Search models / rankings / scenarios
AI Model Rankings
Browse and compare AI models with detailed rankings across multiple domains
Back to Home
General Ranking
Code Ranking
Math Reasoning
Science
Reasoning
Agentic Capability
Multimodal Ranking
Image Generation
Text-to-Video
Image-to-Video
Audio
Rank
Model
Score
Rank
Model
Score
1
Qwen3.8 Max (0902)
Open
84.0
2
Qwen3.7 Plus
75.0
3
Seed 2.1 Pro
75.0
4
DeepSeek V4.1 Flash (Max)
Open
73.0
5
Qwen3.6 Plus
73.0
6
Qwen3.8 27B (Xhigh)
Open
72.0
7
GPT-5.2 (Xhigh)
71.0
9
Kimi K3 (Max)
Open
70.0
8
GPT-6 Astra (Max)
70.0
10
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
69.0
11
GLM 5.3 Flash
Open
66.0
12
Muse Spark
66.0
13
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
65.0
14
Qwen3.6 27B (Reasoning)
Open
65.0
15
Seed 2.1 Turbo
65.0
17
GPT-5.1 (High)
64.0
18
GPT-5.1 (Non-reasoning)
64.0
16
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
64.0
19
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
63.0
20
GPT-5 (High)
63.0
149 items
1
2
3
4
5
•••
8
20 / page
Data source: LLM Stats (zeroeval) · vision benchmark aggregation
· Updated: 2026-10-01