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
GPT-6 Astra (Max)
77.0
2
Atria Dawn Preview
Open
75.0
3
Ling-3.0-flash-Fin
71.0
4
Muse Spark 1.3 (Max)
70.0
5
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
68.0
6
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
67.0
7
Kimi K2.7 Code
Open
65.0
8
Muse Spark 1.1 (Xhigh)
65.0
9
Qwen3.8-Flash-Next
Open
65.0
10
Qwen3.8 Flash
65.0
11
GPT-5.6 Sol (Max)
64.0
12
Qwen3.7 Max
64.0
13
Claude Sonnet 4.6 (Non-reasoning, High Effort)
63.0
14
Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
63.0
15
GLM-5 (Reasoning)
Open
62.0
17
Qwen3.5 397B A17B (Non-reasoning)
Open
62.0
16
Ling 3.0 Flash
62.0
18
Qwen3.8 Max (0902)
Open
61.0
19
Gemini 3.1 Pro Preview
60.0
20
Gemini 3.5 Flash (High)
60.0
109 items
1
2
3
4
5
6
20 / page
Data source: LLM Stats (zeroeval) · agentic benchmark aggregation
· Updated: 2026-10-01