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
47 min
Toate sursele se sincronizează normal
  • Arena · Textacum 3 ore
  • Arena · WebDevacum 3 ore
  • Arena · Visionacum 3 ore
  • Arena · Agentacum 3 ore
  • GPQA Diamondacum 47 de minute
  • SWE-benchacum 47 de minute
  • Terminal-Benchacum 47 de minute
  • ARC-AGI-2acum 47 de minute
Rusă ×1360 din 360 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Muse Wonder (Max)metaoct. 2026—1,5311,504–1,559#14–56
2Gemini 4 Argon (High)googleoct. 2026$2 / $101,5261,503–1,549#1–10
3Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,5211,510–1,532#9–57
4Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5161,497–1,534#2–11
5Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5151,506–1,525#4–20
6Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,5141,505–1,524#2–29
7Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,5081,494–1,522#2–21
8Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,5061,499–1,513#2–25
9Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,5051,497–1,513#1–18
10Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,5011,495–1,507#9–36
11Gemini 3 Progoogleian. 2026—1,5001,491–1,508#23–90
12Claude Opus 5 (High)anthropicsept. 2026$5 / $251,4981,490–1,505#5–11
13Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,4971,478–1,515#13–112
14gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4961,487–1,505#6–25
15claude-opus-4-8-highanthropicsept. 2026$5 / $251,4951,487–1,502#15–33
16Muse Spark 1.1metasept. 2026$1.25 / $4.251,4941,485–1,503#21–115
17Kimi K3 (Max)moonshotiun. 2026$0.25 / $11.941,4941,484–1,503#10–39
18gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4931,483–1,503#16–95
19Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,4931,480–1,505#13–33
20gemini-3.5-flash-mediumgooglesept. 2026$1.50 / $91,4911,482–1,499#10–26
21gpt-6.1-sol-maxopenaioct. 2026$2 / $101,4901,470–1,510#1–15
22gpt-5.4-highopenaisept. 2026$2.50 / $151,4871,479–1,495#12–29
23gemini-3-flashgoogleian. 2026—1,4861,477–1,496#38–153
24qwen3.8-maxalibabaoct. 2026$2 / $61,4851,475–1,495#12–40
25qwen3.7-max-previewalibabaoct. 2026—1,4831,452–1,514#29–73
26Muse Sparkmetasept. 2026—1,4821,466–1,497#16–40
27gpt-5.5-highopenaisept. 2026$5 / $301,4801,473–1,488#9–34
28grok-4.20-beta1xaioct. 2026—1,4791,469–1,490#46–119
29gpt-5.2-chat-latest-20260210openaifeb. 2026—1,4791,470–1,489#44–72
30grok-4.20-beta-0309-reasoningxaisept. 2026—1,4791,471–1,487#49–207
31deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,4781,464–1,492#23–31
32grok-4.20-multi-agent-beta-0309xaioct. 2026—1,4781,470–1,485#48–86
33gpt-5.5-instantopenaisept. 2026—1,4771,466–1,489#52–114
34mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,4751,451–1,499#18–64
35glm-5.2-maxzaiiun. 2026$0.62 / $2.421,4741,465–1,482#9–49

Se afișează Rusă 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.