#18 GLM 5
medium- Gharama
- $0.005
- Muda
- 20.7s
- Tokeni
- 2,068 tok
Z.ai
Toleo: 2026-02-12
Imepimwa tarehe: 2026-05-21 23:44
z-ai/glm-5::medium
744B jumla (40B vinavyotumika)MoEChanzo huria
(medium)
(none)
Muhtasari
GLM 5 hupata alama 8.2 kwenye AI BENCHY na iko nafasi ya #18. Ina reliability 10.0, pass rate 81.7%, gharama jumla $0.237, na wastani wa response time 33.39s.
Kinachofanya GLM 5 iwe ya kipekee: Gharama yake ya benchmark ni ya chini isivyo kawaida kwa kiwango hiki cha score.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- 744B jumla (40B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Chanzo huria
- Leseni
- MIT
8.2
Uthabiti
8.4
10.0
Jumla ya tokeni za matokeo
119,898
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.600 / 1M
Bei ya toleo
$1.920 / 1M
Majaribio yasiyo thabiti
4
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 13:07 Jaribio tena | 7.7 | 10.0 | $0.307 ↑ | Linganisha | |
| 2026-06-04 13:07 Jaribio tena | 7.7 | 10.0 | $0.372 ↑ | Linganisha | |
| 2026-06-04 13:07 Jaribio jipya limeongezwa | 8.3 | 10.0 | $0.228 ↓ | Linganisha | |
| 2026-05-21 23:44 Jaribio tena | 8.2 | 10.0 | $0.237 | Uendeshaji wa sasa | |
| 2026-04-22 12:55 Jaribio la kwanza lililorekodiwa | 8.4 | Haipo | $0.155 | Linganisha |
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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-21 23:44 · Jaribio tena | marudio 60/60 | 8.2 | 8.4 | 10.0 | 14/20 | 4 | 119,898 | 0 | $0.237 | 33.39s |
| 2026-04-22 12:55 · Jaribio la kwanza lililorekodiwa | marudio 54/54 | 8.4 | 8.2 | Haipo | 13/18 | 4 | 78,500 | 0 | $0.155 | 23.34s |
| Tofauti | — | -0.2 | +0.2 | +1 | 0 | +41398 | 0 | +$0.082 | +10045ms |
Ufunikaji wa benchmark unatofautiana: marudio 60/60 (Lengo: marudio 3 kwa kila jaribio) dhidi ya marudio 54/54 (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
GLM 5mediumvsQwen3.7 FlashhighGLM 5mediumvsSeed-2.0-CodelowGLM 5mediumvsClaude Opus 4.8lowGLM 5mediumvsClaude Opus 4.6mediumGLM 5mediumvsSeed-2.0-LitemediumGLM 5mediumvsDeepSeek V4 ProhighGLM 5mediumvsQwen3.8 27BmediumGLM 5mediumvsDeepSeek V4 Flash 0423highGLM 5mediumvsClaude Sonnet 4.6mediumGLM 5mediumvsGPT-5.6 Lunahigh
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 10.0 | 10.0 | |
| Uandishi wa msimbo | 10.0 | 10.0 | |
| Mchanganyiko | 10.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 7.1 | 5.6 | |
| Mahususi kwa domeni | 3.5 | 4.4 | |
| Akili ya jumla | 6.1 | 3.1 | |
| Ufuataji wa maagizo | 10.0 | 10.0 | |
| Utatuzi wa mafumbo | 10.0 | 10.0 | |
| Mwito wa zana | 10.0 | 10.0 | |
| Maarifa ya jumla | 3.0 | 10.0 |