#119 DeepSeek V3.2
medium- Gharama
- $0.001
- Muda
- 53.6s
- Tokeni
- 1,932 tok
DeepSeek
Toleo: 2025-12-01
Imepimwa tarehe: 2026-08-14 03:00
deepseek/deepseek-v3.2::medium
671B jumla (37B vinavyotumika)MoEChanzo huria
(medium)
(none)
Muhtasari
DeepSeek V3.2 hupata alama 7.0 kwenye AI BENCHY na iko nafasi ya #119. Ina reliability 10.0, pass rate 65.2%, gharama jumla $0.078, na wastani wa response time 68.43s.
Kinachofanya DeepSeek V3.2 iwe ya kipekee: Inaonekana zaidi kwenye Mchanganyiko, ambako iko #3; huku Akili ya jumla ikiwa eneo lake dhaifu zaidi kwenye #17.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- 671B jumla (37B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Chanzo huria
- Leseni
- MIT
7.0
Uthabiti
7.4
10.0
Jumla ya tokeni za matokeo
128,787
Jumla ya tokeni za ingizo
101,056
Bei ya ingizo
$0.269 / 1M
Bei ya toleo
$0.400 / 1M
Majaribio yasiyo thabiti
7
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 03:00 Jaribio tena | 7.0 | 10.0 | $0.078 ↑ | Uendeshaji wa sasa | |
| 2026-07-16 23:13 Jaribio jipya limeongezwa | 7.0 | 10.0 | $0.078 ↑ | Linganisha | |
| 2026-06-04 14:41 Jaribio jipya limeongezwa | 7.0 | 10.0 | $0.044 ↓ | Linganisha | |
| 2026-05-22 00:46 Suite imebadilika | 7.0 | 9.1 | $0.037 | Linganisha | |
| 2026-05-08 15:27 Suite imebadilika | 7.2 | 10.0 | $0.031 | Linganisha | |
| 2026-04-20 17:48 Jaribio la kwanza lililorekodiwa | 8.0 | Haipo | $0.029 | Linganisha |
Uendeshaji huu ulitumia suite tofauti ya benchmark. Zingatia mabadiliko ya suite unapochambua mwenendo wa kihistoria.
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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 03:00 · Uendeshaji wa sasa | marudio 66/66 | 7.0 | 7.4 | 10.0 | 11/22 | 7 | 128,787 | 101,056 | $0.078 | 68.43s |
| 2026-07-16 23:13 · Jaribio jipya limeongezwa | marudio 66/66 | 7.0 | 7.4 | 10.0 | 11/22 | 7 | 128,848 | 101,047 | $0.078 | 68.62s |
| Tofauti | — | 0.0 | 0.0 | 0.0 | 0 | 0 | -61 | +9 | -$0.001 | -182ms |
Uendeshaji huu miwili ulitumia suite tofauti za benchmark, hivyo tofauti zinaonyesha mabadiliko ya modeli na ya suite pia.
Historia ya bei
Data ya kihistoria ya bei ya modeli hii kutoka OpenRouter.
| Tarehe | Bei ya ingizo | Bei ya toleo |
|---|---|---|
| 2026-06-04 15:40 | $0.229 / 1M | $0.344 / 1M |
| 2026-07-10 11:30 | $0.215 / 1M | $0.322 / 1M |
| 2026-08-14 12:51 | $0.269 / 1M | $0.400 / 1M |
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
DeepSeek V3.2mediumvsGPT-5.6 SolnoneDeepSeek V3.2mediumvsGLM 5.1mediumDeepSeek V3.2mediumvsGrok 4.3mediumDeepSeek V3.2mediumvsGPT-5.5noneDeepSeek V3.2mediumvsSolar Pro 4highDeepSeek V3.2mediumvsMercury 2mediumDeepSeek V3.2mediumvsStep 3.7 FlashlowDeepSeek V3.2mediumvsGrok 4.20mediumDeepSeek V3.2mediumvsMuse Glimmer 30BlowDeepSeek V3.2mediumvsSeed-2.0-Minimedium
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 8.2 | 7.9 | |
| Uandishi wa msimbo | 6.0 | 7.2 | |
| Mchanganyiko | 7.3 | 5.8 | |
| Uchanganuzi na uchimbaji wa data | 10.0 | 10.0 | |
| Mahususi kwa domeni | 2.9 | 4.4 | |
| Akili ya jumla | 3.4 | 2.5 | |
| Ufuataji wa maagizo | 10.0 | 10.0 | |
| Utatuzi wa mafumbo | 7.0 | 7.2 | |
| Mwito wa zana | 10.0 | 10.0 | |
| Maarifa ya jumla | 3.0 | 10.0 |