#67 Gemini 2.5 Flash
none
SVG batili
- Gharama
- $0.164
- Muda
- 215.5s
- Tokeni
- 65,659 tok
Google
Toleo: 2025-06-17
Imepimwa tarehe: 2026-04-11 01:44
google/gemini-2.5-flash::none
~350B jumla (~20B vinavyotumika)MoEImefungwaMakadirio
(medium)
(none)
Muhtasari
Gemini 2.5 Flash hupata alama 6.2 kwenye AI BENCHY na iko nafasi ya #67. Ina reliability Haipo, pass rate 44.4%, gharama jumla $0.013, na wastani wa response time 903ms.
Kinachofanya Gemini 2.5 Flash iwe ya kipekee: Inaonekana zaidi kwenye Uandishi wa msimbo, ambako iko #1; huku Mbinu za kupinga AI ikiwa eneo lake dhaifu zaidi kwenye #18. Gharama yake ya benchmark ni ya chini isivyo kawaida kwa kiwango hiki cha score. Ni ya haraka kwa kiasi kikubwa ikilinganishwa na modeli zinazofanana.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- ~350B jumla (~20B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Imefungwa
- Leseni
- -
Makadirio bora kulingana na ushahidi wa umma; mtoa huduma hakufichua thamani zote.
6.2
Uthabiti
9.2
Haipo
Jumla ya tokeni za matokeo
1,726
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.300 / 1M
Bei ya toleo
$2.500 / 1M
Majaribio yasiyo thabiti
2
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 02:44 Jaribio tena | 6.0 | 10.0 | $0.017 | Linganisha | |
| 2026-07-16 22:58 Jaribio jipya limeongezwa | 6.2 | 10.0 | $0.017 | Linganisha | |
| 2026-06-04 14:00 Jaribio jipya limeongezwa | 6.2 | 10.0 | $0.016 | Linganisha | |
| 2026-05-22 00:28 Suite imebadilika | 6.2 | 10.0 | $0.015 | Linganisha | |
| 2026-04-11 01:44 Jaribio la kwanza lililorekodiwa | 6.2 | Haipo | $0.013 | 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 | 6.2 | 9.2 | Haipo | 7/18 | 2 | 1,726 | 0 | $0.013 | 903ms |
| 2026-07-16 22:58 · Jaribio jipya limeongezwa | marudio 66/66 | 6.2 | 9.6 | 10.0 | 9/22 | 1 | 1,890 | 39,877 | $0.017 | 6.20s |
| Tofauti | — | 0.0 | -0.4 | -2 | +1 | -164 | -39877 | -$0.004 | -5295ms |
Ufunikaji wa benchmark unatofautiana: marudio 54/54 (Lengo: marudio 3 kwa kila jaribio) dhidi ya marudio 66/66 (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
Ulinganisho wa haraka
Gemini 2.5 FlashnonevsTrinity Large ThinkinglowGemini 2.5 FlashnonevsGPT-5.6 TerranoneGemini 2.5 FlashnonevsNemotron 3 UltranoneInapatikana bureGemini 2.5 FlashnonevsGPT-5 NanomediumGemini 2.5 FlashnonevsQwen3.5 Plus 2026-04-20noneGemini 2.5 FlashnonevsQwen3.5-FlashnoneGemini 2.5 FlashnonevsGemma 4 31BnoneInapatikana bureGemini 2.5 FlashnonevsQwen3.5-35B-A3BnoneGemini 2.5 FlashnonevsQwen3.6 FlashnoneGemini 2.5 FlashnonevsStep 3.5 Flashmedium
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 3.0 | 10.0 | |
| Uandishi wa msimbo | 10.0 | 10.0 | |
| Mchanganyiko | 3.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 10.0 | 10.0 | |
| Mahususi kwa domeni | 5.9 | 7.2 | |
| Akili ya jumla | 5.0 | 10.0 | |
| Ufuataji wa maagizo | 8.0 | 6.8 | |
| Utatuzi wa mafumbo | 5.7 | 10.0 | |
| Mwito wa zana | 10.0 | 10.0 |