GPT, Claude, Gemini, Grok, and DeepSeek are locked in a tight race for the top spot in text understanding, coding, and everyday usefulness. This ranking pits the current top models directly against each other.
| # | Term | Elo |
|---|---|---|
| ๐ฅ |
Claude Opus 4.8
|
1327
174 duels
|
| ๐ฅ |
GPT-5.5
|
1171
189 duels
|
| ๐ฅ |
Gemini 3.1 Pro
|
1096
174 duels
|
| 4 |
DeepSeek V4
|
892
190 duels
|
| 5 |
Grok 4.3 CLOSE
|
890
180 duels
|
| 6 |
Mistral Large
|
737
181 duels
|
| 7 |
Llama 4
|
671
190 duels
|