AI models, ranked by real usage

What is really running on Elosia: the most used, the best performing, the best value for money.

Most used

130 models tracked
Models46

Top performance

index /100
1Claude Opus 5Claude87
2Claude Fable 5Claude82
3Claude Opus 4.8Claude82
4GPT-5.6 Sol ProGPT80
5GPT-5.2 CodexGPT79
6Claude Opus 4.7Claude78
7Kimi K3MoonshotAi76
8Claude Opus 4.6Claude76
9Gemini 3.7 FlashGemini76
10Gemini 3.1 ProGemini76

Best value

perf ÷ price
1DeepSeek v4 Flash 0731DeepSeek54$0.11
2Laguna S 2.1Poolside52$0.11
3DeepSeek v3.2DeepSeek60$0.30
4Minimax 2.5Minimax54$0.39
5DeepSeek v3.1DeepSeek54$0.43
6DeepSeek v3 0324DeepSeek53$0.48
7Z.ai GLM 5.2Z.ai64$0.60
8Minimax M3Minimax53$0.52
9Qwen 3.5 27BQwen55$0.54
10Gemini 3.7 FlashGemini76$0.75

By provider

cumulative usage share
Providers8

Favorites by use case

Coding

View all →
  1. 1CClaude Opus 5
  2. 2CClaude Fable 5
  3. 3CClaude Opus 4.8

Analysis

View all →
  1. 1CClaude Opus 5
  2. 2CClaude Fable 5
  3. 3CClaude Opus 4.8

Research

View all →
  1. 1CClaude Opus 5
  2. 2CClaude Fable 5
  3. 3CClaude Opus 4.8

Creative Writing

View all →
  1. 1CClaude Opus 5
  2. 2CClaude Opus 4.8
  3. 3CClaude Opus 4.7

Mathematics

View all →
  1. 1GGPT-5.6 Sol Pro
  2. 2GGemini 3.1 Pro
  3. 3GGPT-5.1

Translation

View all →
  1. 1QQwen 3.7 Max
  2. 2QQwen 3.5 27B
  3. 3USolar Pro 4

Browse all models

14 collections
ProvidersClaudeDeepSeekGeminiByteDanceGPTGrokMinimaxMistralMoonshotAiQwenZ.ai
TiersFlagshipBalancedCompactSpecialized

Aggregated, anonymized data. Performance is a benchmark index. Prices are real, per 1M tokens. Updated daily.