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
22.310
Ultima sincronizare
33 min
Toate sursele se sincronizează normal
  • Arena · Textacum 1 oră
  • Arena · WebDevacum 1 oră
  • Arena · Visionacum 1 oră
  • Arena · Agentacum 1 oră
  • GPQA Diamondacum 33 de minute
  • SWE-benchacum 33 de minute
  • Terminal-Benchacum 33 de minute
  • ARC-AGI-2acum 33 de minute

qwen3.8-max

1,301±7

1,293CI1,308

alibabaoct. 2026oscilație #12–#40

Vision Arena ×1150 din 150 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1claude-fable-5-highanthropicsept. 2026$10 / $501,3081,301–1,315#4–20
2qwen3.8-maxalibabaoct. 2026$2 / $61,3011,293–1,308#12–40
3claude-opus-4-6-highanthropicsept. 2026$5 / $251,2991,293–1,306#2–25
4claude-opus-4-7anthropicsept. 2026$5 / $251,2981,292–1,305#1–18
5gemini-3.7-flash-highgoogleoct. 2026$0.75 / $3.751,2971,287–1,307#9–57
6gpt-6.1-sol-maxopenaioct. 2026$2 / $101,2941,280–1,308#1–15
7muse-sparkmetasept. 2026—1,2941,285–1,303#16–40
8muse-spark-1.2 (xHigh)metaoct. 2026$1.25 / $4.251,2931,279–1,307#13–112
9claude-opus-5.5-highanthropicoct. 2026$4 / $201,2931,280–1,305#2–11
10muse-spark-1.3-maxmetasept. 2026$1.25 / $4.251,2901,280–1,300#13–33
11gemini-3-progoogleian. 2026—1,2891,282–1,297#23–90
12gemini-3.8-flash-highgoogleoct. 2026$0.83 / $4.131,2891,279–1,300#2–29
13claude-opus-5-highanthropicsept. 2026$5 / $251,2871,281–1,294#5–11
14gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,2871,280–1,294#6–25
15claude-fable-5.1-maxanthropicsept. 2026$10 / $501,2861,277–1,296#2–21
16gpt-6-astra-maxopenaisept. 2026$10 / $501,2861,275–1,297#1–18
17gpt-5.5openaisept. 2026$5 / $301,2861,280–1,292#9–34
18claude-opus-4-8-highanthropicsept. 2026$5 / $251,2861,279–1,292#15–33
19gemini-3.5-flash-mediumgooglesept. 2026$1.50 / $91,2851,278–1,292#10–26
20gpt-5.4-highopenaisept. 2026$2.50 / $151,2851,279–1,291#12–29
21gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,2811,273–1,289#16–95
22grok-4.5xaisept. 2026$2 / $61,2801,273–1,287#29–70
23muse-spark-1.1metasept. 2026$1.25 / $4.251,2801,273–1,287#21–115
24gemini-3.1-pro-previewgooglesept. 2026$2 / $121,2801,275–1,285#9–36
25gpt-5.2-chat-latest-20260210openaifeb. 2026—1,2781,271–1,284#44–72
26gpt-5.5-instantopenaisept. 2026—1,2761,267–1,284#52–114
27claude-sonnet-4-6anthropicsept. 2026$3 / $151,2751,269–1,281#38–77
28glm-5.3-flashzaiaug. 2026$0.05 / $0.201,2731,266–1,280#26–60
29gemini-3-flashgoogleian. 2026—1,2731,268–1,278#38–153
30gpt-6-sol-maxopenaioct. 2026$2 / $101,2701,258–1,283#7–53
31gpt-5.6-terra-xhighopenaisept. 2026$2 / $121,2681,261–1,275#13–59
32claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,2661,252–1,280#4–26
33gemini-3.5-flash-litegoogleoct. 2026$0.30 / $2.501,2661,258–1,274#62–171
34kimi-k2.6moonshotapr. 2026$0.65 / $3.411,2651,259–1,272#29–78
35qwen3.7-plusalibabasept. 2026$0.32 / $1.281,2641,257–1,271#51–124

Se afișează Vision Arena 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.