AI BENCHY Compare
OpenAI: GPT-5.2 vs xAI: Grok 4.20
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-02
| Kipimo | GPT-5.2 GPT-5.2 medium | Grok 4.20 Grok 4.20 medium |
|---|---|---|
| Alama | 7.3 | 7.1 |
| Nafasi | #36 | #40 |
| Uthabiti | 8.0 | 8.2 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 70.6% | 66.7% |
| Majaribio yasiyo thabiti | 4 | 4 |
| Jumla ya uendeshaji | 51 | 51 |
| Gharama kwa matokeo | 3.131 | 7.358 |
| Jumla ya gharama | $0.314 | $0.663 |
| Bei ya ingizo | $1.750 / 1M | $2.000 / 1M |
| Bei ya toleo | $14.000 / 1M | $6.000 / 1M |
| Tokeni za matokeo | 2,238 | 1,494 |
| Tokeni za hoja | 16,811 | 97,078 |
| Muda wa majibu (wastani) | 13.93s | 9.50s |
| Muda wa majibu (upeo) | 77.80s | 29.87s |
| Muda wa majibu (jumla) | 139.29s | 161.54s |
Alama dhidi ya gharama ya jumla
Muda wa majibu (wastani)
Alama vs Muda wa majibu (wastani)
Jumla ya tokeni za matokeo
Alama vs Jumla ya tokeni za matokeo
Mgawanyo wa kategoria
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Claude Sonnet 4.6nonevsGPT-5.2mediumClaude Sonnet 4.6nonevsGrok 4.20mediumQwen3.5 Plus 2026-02-15nonevsGrok 4.20mediumGemma 4 31BnonevsGrok 4.20mediumGrok 4.20mediumvsGLM 5noneGPT-5.3 ChatnonevsGrok 4.20mediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.2mediumGPT-5.2mediumvsQwen3.5 Plus 2026-02-15noneGemma 4 31BnonevsGPT-5.2mediumGPT-5.2mediumvsGLM 5noneGrok 4.20mediumvsMiMo-V2-OmninoneGPT-5.2 ChatnonevsGrok 4.20medium