#133 MiniMax M2.7
medium- Gharama
- $0.022
- Muda
- 22.8s
- Tokeni
- 9,250 tok
Minimax
Toleo: 2026-03-18
Imepimwa tarehe: 2026-05-21 23:52
minimax/minimax-m2.7::medium
230B jumla (10B vinavyotumika)MoEUzani unapatikana Muhtasari
MiniMax M2.7 hupata alama 5.0 kwenye AI BENCHY na iko nafasi ya #133. Ina reliability 8.3, pass rate 46.7%, gharama jumla $0.104, na wastani wa response time 29.96s.
Taarifa za modeli
Ilifanyiwa utafiti tarehe 2026-08-12
- Vigezo
- 230B jumla (10B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Uzani unapatikana
- Leseni
- MiniMax modified MIT
5.0
Uthabiti
5.9
8.3
Jumla ya tokeni za matokeo
81,525
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.279 / 1M
Bei ya toleo
$1.200 / 1M
Majaribio yasiyo thabiti
10
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 01:38 Jaribio tena | 5.0 | 10.0 | $0.208 | Linganisha | |
| 2026-07-16 21:18 Jaribio jipya limeongezwa | 5.0 | 10.0 | $0.196 | Linganisha | |
| 2026-06-04 13:26 Jaribio jipya limeongezwa | 5.3 | 7.8 | $0.124 ↓ | Linganisha | |
| 2026-05-21 23:52 Suite imebadilika | 5.0 | 8.3 | $0.104 | Uendeshaji wa sasa | |
| 2026-04-11 01:44 Jaribio la kwanza lililorekodiwa | 5.3 | Haipo | $0.091 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-21 23:52 · Suite imebadilika | marudio 60/60 | 5.0 | 5.9 | 8.3 | 4/20 | 10 | 81,525 | 0 | $0.104 | 29.96s |
| 2026-04-11 01:44 · Jaribio la kwanza lililorekodiwa | marudio 54/54 | 5.3 | 5.5 | Haipo | 4/18 | 10 | 67,771 | 0 | $0.091 | 31.08s |
| Tofauti | — | -0.2 | +0.4 | 0 | 0 | +13754 | 0 | +$0.013 | -1116ms |
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
MiniMax M2.7mediumvsNorth Mini CodenoneInapatikana bureMiniMax M2.7mediumvsMercury 2.5 PreviewlowMiniMax M2.7mediumvsQwen3.5-9BnoneMiniMax M2.7mediumvsLaguna S 2.1lowInapatikana bureMiniMax M2.7mediumvsMiMo-V2.5noneMiniMax M2.7mediumvsDeepSeek V3.2noneMiniMax M2.7mediumvsMercury 2.5lowMiniMax M2.7mediumvsGPT-4o-mininoneMiniMax M2.7mediumvsQwen3 Coder NextnoneMiniMax M2.7mediumvsMercury 2.5 Previewnone
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 7.9 | 6.3 | |
| Uandishi wa msimbo | 6.7 | 9.6 | |
| Mchanganyiko | 4.7 | 1.6 | |
| Uchanganuzi na uchimbaji wa data | 6.3 | 5.8 | |
| Mahususi kwa domeni | 3.0 | 10.0 | |
| Akili ya jumla | 3.9 | 2.5 | |
| Ufuataji wa maagizo | 3.8 | 1.6 | |
| Utatuzi wa mafumbo | 3.5 | 4.4 | |
| Mwito wa zana | 4.7 | 1.6 | |
| Maarifa ya jumla | 3.0 | 10.0 |