#15 Gemma 4 31B
medium- Gharama
- $0.002
- Muda
- 45.7s
- Tokeni
- 2,696 tok
Google
Toleo: 2026-04-02
Imepimwa tarehe: 2026-04-14 00:56
google/gemma-4-31b-it::medium
(medium)
(none)
Muhtasari
Gemma 4 31B hupata alama 8.3 kwenye AI BENCHY na iko nafasi ya #15. Ina reliability Haipo, pass rate 79.6%, gharama jumla $0.018, na wastani wa response time 24.88s.
Kinachofanya Gemma 4 31B iwe ya kipekee: Inaonekana zaidi kwenye Mahususi kwa domeni, ambako iko #1; huku Uandishi wa msimbo ikiwa eneo lake dhaifu zaidi kwenye #17. Gharama yake ya benchmark ni ya chini isivyo kawaida kwa kiwango hiki cha score.
8.3
Uthabiti
9.2
Haipo
Jumla ya tokeni za matokeo
40,684
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.130 / 1M
Bei ya toleo
$0.380 / 1M
Majaribio yasiyo thabiti
2
Majaribio yasiyo thabiti yalikuwa na matokeo mchanganyiko kati ya run (angalau kupita moja na kufeli moja).
Onyesho la kizazi
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 14:27 Jaribio jipya limeongezwa | 7.9 | 8.9 | $0.035 ↓ | Linganisha | |
| 2026-05-22 00:35 Suite imebadilika | 8.0 | 6.7 | $0.029 | Linganisha | |
| 2026-04-14 00:56 Jaribio la kwanza lililorekodiwa | 8.3 | Haipo | $0.018 | Uendeshaji wa sasa |
Ulinganisho wa uendeshaji
| Uendeshaji | 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) |
|---|---|---|---|---|---|---|---|---|---|
| 2026-04-14 00:56 · Jaribio la kwanza lililorekodiwa | 8.3 | 9.2 | Haipo | 13/18 | 2 | 40,684 | 0 | $0.018 | 24.88s |
| 2026-05-22 00:35 · Suite imebadilika | 8.0 | 9.2 | 6.7 | 14/20 | 2 | 69,291 | 0 | $0.029 | 35.51s |
| Tofauti | +0.4 | 0.0 | -1 | 0 | -28607 | 0 | -$0.012 | -10626ms |
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
Gemma 4 31BmediumInapatikana burevsMiMo-V2.5mediumGemma 4 31BmediumInapatikana burevsgpt-oss-120bmediumInapatikana bureGemma 4 31BmediumInapatikana burevsQwen3.6 35B A3BmediumGemma 4 31BmediumInapatikana burevsGPT-5 NanomediumGemma 4 31BmediumInapatikana burevsStep 3.5 FlashmediumGemma 4 31BmediumInapatikana burevsGemini 3.5 FlashhighGemma 4 31BmediumInapatikana burevsGemini 3 Flash PreviewmediumGemma 4 31BmediumInapatikana burevsNemotron 3 Ultra 550b A55bmediumInapatikana bureGemma 4 31BmediumInapatikana burevsGPT-5.5low
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 10.0 | 10.0 | |
| Uandishi wa msimbo | 4.7 | 1.6 | |
| Mchanganyiko | 3.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 10.0 | 10.0 | |
| Mahususi kwa domeni | 7.7 | 10.0 | |
| Akili ya jumla | 10.0 | 10.0 | |
| Ufuataji wa maagizo | 10.0 | 10.0 | |
| Utatuzi wa mafumbo | 8.8 | 7.9 | |
| Mwito wa zana | 3.0 | 10.0 |