#13 Gemini 3 PRO Preview
medium
No endpoints found for google/gemini-3-pro-preview.
- Gharama
- $0.000
- Muda
- 0.1s
- Tokeni
- 0 tok
Google
Toleo: 2025-11-18
Imepimwa tarehe: 2026-04-11 01:44
google/gemini-3-pro-preview::medium
~1.2T jumla (~20B vinavyotumika)MoEImefungwaMakadirio Muhtasari
Gemini 3 PRO Preview hupata alama 8.4 kwenye AI BENCHY na iko nafasi ya #13. Ina reliability Haipo, pass rate 77.8%, gharama jumla $0.197, na wastani wa response time 9.06s.
Modeli iliyohifadhiwa: modeli hii haitasasishwa tena wala kujaribiwa kwenye majaribio mapya.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- ~1.2T jumla (~20B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Imefungwa
- Leseni
- -
Makadirio bora kulingana na ushahidi wa umma; mtoa huduma hakufichua thamani zote.
8.4
Uthabiti
10.0
Haipo
Jumla ya tokeni za matokeo
11,592
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.000 / 1M
Bei ya toleo
$0.000 / 1M
Majaribio yasiyo thabiti
0
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 |
|---|---|---|---|---|---|
| 2026-06-04 14:03 Jaribio jipya limeongezwa | 6.0 | Haipo | $0.385 ↑ | Linganisha | |
| 2026-05-22 00:29 Suite imebadilika | 8.1 | Haipo | $0.197 | Linganisha | |
| 2026-04-11 01:44 Jaribio la kwanza lililorekodiwa | 8.4 | Haipo | $0.197 | Uendeshaji wa sasa |
Ulinganisho wa uendeshaji
| Uendeshaji | Ufunikaji wa benchmark | Alama | Uthabiti | Uaminifu | Majaribio sahihi | Majaribio yasiyo thabiti | Jumla ya tokeni za matokeo | Jumla ya tokeni za ingizo | Jumla ya gharama | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · Jaribio la kwanza lililorekodiwa | marudio 54/54 | 8.4 | 10.0 | Haipo | 14/18 | 0 | 11,592 | 0 | $0.197 | 9.06s |
| 2026-06-04 14:03 · Jaribio jipya limeongezwa | marudio 63/63 | 6.0 | 9.5 | Haipo | 14/21 | 0 | 11,592 | 28,848 | $0.385 | 9.05s |
| Tofauti | — | +2.4 | +0.5 | 0 | 0 | 0 | -28848 | -$0.188 | +4ms |
Ufunikaji wa benchmark unatofautiana: marudio 54/54 (Lengo: marudio 3 kwa kila jaribio) dhidi ya marudio 63/63 (Lengo: marudio 3 kwa kila jaribio). Jumla na vipimo vinavyoathiriwa na marudio haviwezi kulinganishwa moja kwa moja.
Uendeshaji huu miwili ulitumia suite tofauti za benchmark, hivyo tofauti zinaonyesha mabadiliko ya modeli na ya suite pia.
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
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 10.0 | 10.0 | |
| Uandishi wa msimbo | 3.0 | 10.0 | |
| Mchanganyiko | 3.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 10.0 | 10.0 | |
| Mahususi kwa domeni | 5.3 | 10.0 | |
| Akili ya jumla | 10.0 | 10.0 | |
| Ufuataji wa maagizo | 9.8 | 10.0 | |
| Utatuzi wa mafumbo | 10.0 | 10.0 | |
| Mwito wa zana | 10.0 | 10.0 |