#73 gpt-oss-120b
medium- Gharama
- $0.001
- Muda
- 26.7s
- Tokeni
- 555 tok
OpenAI
Toleo: 2025-08-05
Imepimwa tarehe: 2026-04-21 12:42
openai/gpt-oss-120b::medium
117B jumla (5.1B vinavyotumika)MoEChanzo huria
(medium)
(none)
Muhtasari
gpt-oss-120b hupata alama 5.8 kwenye AI BENCHY na iko nafasi ya #73. Ina reliability Haipo, pass rate 51.9%, gharama jumla $0.011, na wastani wa response time 16.08s.
Kinachofanya gpt-oss-120b 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
- 117B jumla (5.1B vinavyotumika)
- Muundo
- MoE
- Upatikanaji
- Chanzo huria
- Leseni
- Apache-2.0
5.8
Uthabiti
7.2
Haipo
Jumla ya tokeni za matokeo
50,372
Jumla ya tokeni za ingizo
0
Bei ya ingizo
$0.000 / 1M
Bei ya toleo
$0.000 / 1M
Majaribio yasiyo thabiti
6
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 02:08 Jaribio tena | 6.1 | 10.0 | $0.019 ↓ | Linganisha | |
| 2026-07-16 22:24 Jaribio jipya limeongezwa | 6.1 | 10.0 | $0.019 ↓ | Linganisha | |
| 2026-06-04 13:44 Jaribio jipya limeongezwa | 6.1 | 10.0 | $0.013 ↓ | Linganisha | |
| 2026-05-22 00:18 Suite imebadilika | 5.6 | 10.0 | $0.012 | Linganisha | |
| 2026-04-21 12:42 Jaribio la kwanza lililorekodiwa | 5.8 | Haipo | $0.011 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-21 12:42 · Jaribio la kwanza lililorekodiwa | marudio 54/54 | 5.8 | 7.2 | Haipo | 7/18 | 6 | 50,372 | 0 | $0.011 | 16.08s |
| 2026-06-04 13:44 · Jaribio jipya limeongezwa | marudio 63/63 | 6.1 | 8.0 | 10.0 | 9/21 | 5 | 70,246 | 39,084 | $0.013 | 22.28s |
| Tofauti | — | -0.3 | -0.8 | -2 | +1 | -19874 | -39084 | -$0.003 | -6203ms |
Ufunikaji wa benchmark unatofautiana: marudio 54/54 (Lengo: marudio 3 kwa kila jaribio) dhidi ya marudio 63/63 (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
gpt-oss-120bmediumInapatikana burevsQwen3.5-35B-A3Bmediumgpt-oss-120bmediumInapatikana burevsQwen3.7 Flashnonegpt-oss-120bmediumInapatikana burevsGemini 3.1 Flash Liteminimalgpt-oss-120bmediumInapatikana burevsGemini 3.1 Flash Litenonegpt-oss-120bmediumInapatikana burevsClaude Sonnet 5nonegpt-oss-120bmediumInapatikana burevsQwen3.5-Flashmediumgpt-oss-120bmediumInapatikana burevsGPT-5.6 Lunalowgpt-oss-120bmediumInapatikana burevsInklinglowgpt-oss-120bmediumInapatikana burevsGemma 4 31BmediumInapatikana buregpt-oss-120bmediumInapatikana burevsTrinity Large Thinkingmedium
Mgawanyo wa kategoria
| Kategoria | Alama | Uthabiti | Majaribio sahihi |
|---|---|---|---|
| Mbinu za kupinga AI | 6.7 | 9.9 | |
| Uandishi wa msimbo | 4.3 | 1.1 | |
| Mchanganyiko | 10.0 | 10.0 | |
| Uchanganuzi na uchimbaji wa data | 6.4 | 5.9 | |
| Mahususi kwa domeni | 2.9 | 4.4 | |
| Akili ya jumla | 4.3 | 10.0 | |
| Ufuataji wa maagizo | 9.9 | 10.0 | |
| Utatuzi wa mafumbo | 3.2 | 4.7 | |
| Mwito wa zana | 9.8 | 10.0 |