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

154 models tracked
Models40

Top performance

index /100
1Claude Opus 5.5Claude88
2GPT-6 AstraGPT86
3Claude Sonnet 5.5Claude82
4Claude Opus 5Claude82
5Claude Fable 5.1Claude81
6Claude Opus 4.8Claude79
7GPT-5.2 CodexGPT79
8Claude Fable 5Claude79
9GPT-6.1 SolGPT78
10Gemini 3.8 FlashGemini77

Best value

perf ÷ price
1DeepSeek v4.1 FlashDeepSeek56$0.05
2Z.ai GLM 5.3 FlashZ.ai50$0.08
3Claude Haiku 5.5Claude66$0.20
4MiMo v2.6 FlashXiaomi57$0.18
5Qwen 3.8 Omni FlashQwen66$0.23
6Qwen 3.8 FlashQwen55$0.23
7DeepSeek v3.2DeepSeek60$0.32
8Z.ai GLM 5.3Z.ai62$0.41
9MiMo v2.6 ProXiaomi73$0.54
10DeepSeek v3.1DeepSeek53$0.43

By provider

cumulative usage share
Providers7

Favorites by use case

Coding

View all →
  1. 1CClaude Opus 5.5
  2. 2GGPT-6 Astra
  3. 3CClaude Sonnet 5.5

Analysis

View all →
  1. 1CClaude Opus 5.5
  2. 2GGPT-6 Astra
  3. 3CClaude Sonnet 5.5

Research

View all →
  1. 1CClaude Opus 5.5
  2. 2GGPT-6 Astra
  3. 3CClaude Sonnet 5.5

Creative Writing

View all →
  1. 1CClaude Opus 5.5
  2. 2CClaude Opus 5
  3. 3CClaude Opus 4.8

Mathematics

View all →
  1. 1GGPT-6 Astra
  2. 2GGemini 3.1 Pro
  3. 3GGemini 4 Argon

Translation

View all →
  1. 1QQwen 3.8 Omni Flash
  2. 2QQwen 3.7 Max
  3. 3QQwen 3.5 27B

Browse all models

14 collections
ProvidersClaudeDeepSeekGeminiByteDanceGPTGrokMinimaxMistralMoonshotAiQwenXiaomiZ.ai
TiersFlagshipBalancedCompactSpecialized

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