Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

Benchmark-uri

Surse
8
Intrări urmărite
22.318
Ultima sincronizare
39 min
Toate sursele se sincronizează normal
  • Arena · Textacum 2 ore
  • Arena · WebDevacum 2 ore
  • Arena · Visionacum 2 ore
  • Arena · Agentacum 2 ore
  • GPQA Diamondacum 39 de minute
  • SWE-benchacum 39 de minute
  • Terminal-Benchacum 39 de minute
  • ARC-AGI-2acum 39 de minute
Engleză ×1396 din 396 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Gemini 4 Argon (High)googleoct. 2026$2 / $101,5321,518–1,546#1–10
2Muse Wonder (Max)metaoct. 2026—1,5181,502–1,534#14–56
3Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,5141,509–1,518#2–25
4Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5131,507–1,518#4–21
5Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5111,500–1,522#2–11
6Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,5101,505–1,515#1–18
7Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,5001,492–1,508#13–33
8Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,4991,491–1,507#2–22
9Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,4991,492–1,505#2–30
10Muse Sparkmetasept. 2026—1,4961,489–1,504#16–41
11gpt-6.1-sol-maxopenaioct. 2026$2 / $101,4951,483–1,508#1–15
12mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,4951,480–1,510#19–64
13Kimi K3 (Max)moonshotiun. 2026$0.24 / $11.941,4951,488–1,501#10–40
14Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,4931,483–1,504#13–112
15Claude Opus 5 (High)anthropicsept. 2026$5 / $251,4931,488–1,498#5–11
16qwen3.8-maxalibabaoct. 2026$2 / $61,4911,485–1,498#12–41
17claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,4911,479–1,503#4–26
18Muse Spark 1.1metasept. 2026$1.25 / $4.251,4901,485–1,496#21–115
19claude-opus-4-8-highanthropicsept. 2026$5 / $251,4901,485–1,495#15–33
20Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,4901,486–1,494#9–36
21gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4891,484–1,495#6–24
22glm-5.3-maxzaiaug. 2026$0.08 / $1.401,4881,481–1,495#18–53
23gpt-6-astra-maxopenaisept. 2026$10 / $501,4871,478–1,496#1–18
24Gemini 3 Progoogleian. 2026—1,4871,482–1,493#23–91
25gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4871,481–1,492#16–95
26deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,4861,477–1,495#14–30
27Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,4841,478–1,491#9–57
28gpt-5.5-highopenaisept. 2026$5 / $301,4841,480–1,489#9–34
29claude-sonnet-4-6anthropicsept. 2026$3 / $151,4831,478–1,487#39–78
30glm-5.2-maxzaiiun. 2026$0.62 / $2.421,4821,477–1,487#9–49
31claude-opus-4-5-20251101-high-32kanthropicnov. 2025—1,4821,477–1,488#36–94
32gpt-5.2-chat-latest-20260210openaifeb. 2026—1,4821,476–1,487#44–72
33grok-4.20-beta1xaioct. 2026—1,4811,475–1,487#46–119
34glm-5.1zaiapr. 2026$0.97 / $3.041,4811,476–1,485#44–75
35glm-5.3-flashzaiaug. 2026$0.05 / $0.201,4791,473–1,486#26–59

Se afișează Engleză exact așa cum a publicat-o sursa — propriul scor și interval de încredere, fără mix. Selectează o a doua axă ca să construiești un scor compus ponderat.

Puținele lucruri din AI și cuantic care au contat cu adevărat săptămâna asta — rezumate cinstit.

Un e-mail pe săptămână. Dezabonare dintr-un clic. Fără urmărire, fără partajare.