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
22.308
Ultima sincronizare
33 min
Toate sursele se sincronizează normal
  • Arena · Textacum 33 de minute
  • Arena · WebDevacum 33 de minute
  • Arena · Visionacum 33 de minute
  • Arena · Agentacum 33 de minute
  • GPQA Diamondacum 57 de minute
  • SWE-benchacum 57 de minute
  • Terminal-Benchacum 57 de minute
  • ARC-AGI-2acum 57 de minute
WebDev Arena ×1139 din 139 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1claude-opus-5.5-maxanthropicoct. 2026$4 / $201,8111,797–1,826#2–11
2gpt-6-astra-maxopenaisept. 2026$10 / $501,7801,770–1,791#1–18
3claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,7741,760–1,788#4–26
4gpt-6.1-sol-maxopenaioct. 2026$2 / $101,7601,746–1,774#1–15
5claude-fable-5.1-maxanthropicsept. 2026$10 / $501,7431,734–1,752#2–21
6claude-opus-5-maxanthropicsept. 2026$5 / $251,6901,684–1,696#5–11
7gpt-6-sol-maxopenaioct. 2026$2 / $101,6861,675–1,697#7–53
8Gemini 4 Argon (High)googleoct. 2026$2 / $101,6781,663–1,694#1–10
9Qwen3.8-Max (0902)alibabaoct. 2026$2 / $61,6741,666–1,681#12–40
10qwen3.8-max-0902alibabaoct. 2026$2 / $61,6731,666–1,680#23–155
11muse-spark-1.3-maxmetasept. 2026$1.25 / $4.251,6591,650–1,667#13–33
12kimi-k3-maxmoonshotiun. 2026$0.25 / $11.941,6551,649–1,661#10–39
13muse-wonder-maxmetaoct. 2026—1,6511,633–1,669#14–56
14grok-4.7-xhighxaioct. 2026$2 / $61,6401,630–1,650#21–72
15mimo-v2.6-flashxiaomisept. 2026$0.14 / $0.281,6351,625–1,645#19–88
16qwen3.8-flash-nextalibabaaug. 2026—1,6331,625–1,641#53–285
17hy4-previewtencentaug. 2026$0.75 / $2.251,6321,622–1,641#32–136
18mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,6251,615–1,635#18–64
19Claude Fable 5 (High)anthropicsept. 2026$10 / $501,6251,619–1,631#4–20
20glm-5.3-maxzaiaug. 2026$0.08 / $1.401,6211,613–1,629#18–52
21deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,6191,608–1,629#23–31
22Grok 4.6 (High)xaisept. 2026$2 / $61,6171,610–1,625#15–52
23gpt-5.6-sol-xhigh (codex-harness)openaisept. 2026$4 / $201,6171,611–1,623#6–25
24glm-5.3-flashzaiaug. 2026$0.05 / $0.201,6061,599–1,613#26–60
25GLM-5.2 (Max)zaiiun. 2026$0.62 / $2.421,6051,598–1,611#9–49
26qwen3.8-27balibabaaug. 2026$0.24 / $2.201,5941,588–1,601#32–213
27Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,5911,584–1,597#9–57
28Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,5851,578–1,593#2–29
29claude-haiku-5.5-highanthropicoct. 2026$0.10 / $0.501,5851,573–1,597#43–277
30deepseek-v4-pro-high-20260813deepseekaug. 2026$0.66 / $1.981,5821,573–1,592#17–54
31gpt-6-luna-maxopenaioct. 2026$0.10 / $0.501,5821,575–1,588#30–85
32deepseek-v4-flash-highdeepseekiul. 2026$0.02 / $0.451,5821,572–1,591#42–184
33Step 5 Preview (High)stepfunsept. 2026$1 / $2.701,5651,555–1,575#37–159
34claude-opus-4-7-highanthropicsept. 2026$5 / $251,5581,552–1,563#1–18
35claude-opus-4-8-highanthropicsept. 2026$5 / $251,5561,550–1,562#15–33

Se afișează WebDev 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.