#77 xAI: Grok 4.20
medium- Gharama
- $0.041
- Muda
- 110.3s
- Tokeni
- 16,336 tok
X AI
Toleo: 2026-03-31
Imepimwa tarehe: 2026-05-22 00:32
x-ai/grok-4.20::medium
~1T jumla (~100B vinavyotumika)MoEImefungwaMakadirio
(medium)
(none)
Muhtasari
Grok 4.20 hupata alama 6.7 kwenye AI BENCHY na iko nafasi ya #77. Ina reliability 10.0, pass rate 61.7%, gharama jumla $0.832, na wastani wa response time 19.09s.
Kinachofanya Grok 4.20 iwe ya kipekee: Inaonekana zaidi kwenye Mahususi kwa domeni, ambako iko #2; huku Uandishi wa msimbo ikiwa eneo lake dhaifu zaidi kwenye #17.
Kidokezo cha utambulisho
Grok 4.20 Beta ilikuwa toleo la awali la Grok 4.20.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- ~1T jumla (~100B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Imefungwa
- Leseni
- -
Makadirio bora kulingana na ushahidi wa umma; mtoa huduma hakufichua thamani zote.
6.7
Uthabiti
8.0
10.0
Jumla ya tokeni za matokeo
158,105
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$1.250 / 1M
Bei ya toleo
$2.500 / 1M
Majaribio yasiyo thabiti
5
Majaribio yasiyo thabiti yalikuwa na matokeo mchanganyiko kati ya run (angalau kupita moja na kufeli moja).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Historia ya uendeshaji
| Imepimwa tarehe | Alama | Uaminifu | Majaribio sahihi | Jumla ya gharama | Linganisha |
|---|---|---|---|---|---|
| 2026-08-14 02:57 Jaribio tena | 7.0 | 10.0 | $0.805 ↓ | Linganisha | |
| 2026-07-16 23:07 Jaribio jipya limeongezwa | 7.1 | 10.0 | $0.777 ↓ | Linganisha | |
| 2026-06-04 14:17 Jaribio jipya limeongezwa | 7.1 | 10.0 | $0.609 ↓ | Linganisha | |
| 2026-05-22 00:32 Suite imebadilika | 6.7 | 10.0 | $0.832 | Uendeshaji wa sasa | |
| 2026-05-08 15:32 Suite imebadilika | 6.9 | 10.0 | $0.756 | Linganisha | |
| 2026-04-11 01:44 Jaribio la kwanza lililorekodiwa | 7.0 | Haipo | $0.743 | Linganisha |
Uendeshaji huu ulitumia suite tofauti ya benchmark. Zingatia mabadiliko ya suite unapochambua mwenendo wa kihistoria.
Chati
Chagua modeli ya kwanza, kisha bofya modeli ya pili kufungua ukurasa wa kulinganisha bega kwa bega.
Modeli bora kwa alama
Alama vs Jumla ya gharama
Muda wa majibu (wastani)
Alama vs Muda wa majibu (wastani)
Jumla ya tokeni za matokeo
Alama vs Jumla ya tokeni za matokeo
Ulinganisho wa haraka
Grok 4.20mediumvsMercury 2mediumGrok 4.20mediumvsSeed-2.0-MinimediumGrok 4.20mediumvsGPT-5.5noneGrok 4.20mediumvsKimi K2.5mediumGrok 4.20mediumvsGLM 5.1mediumGrok 4.20mediumvsKAT-Coder-Pro V2.5mediumGrok 4.20mediumvsDeepSeek V3.2mediumGrok 4.20mediumvsQwen3.7 FlashmediumGrok 4.20mediumvsGPT-5.6 SolnoneGrok 4.20mediumvsSeed-2.0-Codehigh
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 8.2 | 7.9 | |
| Uandishi wa msimbo | 4.1 | 1.8 | |
| Mchanganyiko | 10.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 10.0 | 10.0 | |
| Mahususi kwa domeni | 5.3 | 10.0 | |
| Akili ya jumla | 3.9 | 2.6 | |
| Ufuataji wa maagizo | 7.3 | 6.0 | |
| Utatuzi wa mafumbo | 7.7 | 10.0 | |
| Mwito wa zana | 3.0 | 10.0 | |
| Maarifa ya jumla | 3.0 | 10.0 |