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
43 min
Toate sursele se sincronizează normal
  • Arena · Textacum 1 oră
  • Arena · WebDevacum 1 oră
  • Arena · Visionacum 1 oră
  • Arena · Agentacum 1 oră
  • GPQA Diamondacum 43 de minute
  • SWE-benchacum 43 de minute
  • Terminal-Benchacum 43 de minute
  • ARC-AGI-2acum 43 de minute
Japoneză ×1263 din 263 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,5501,509–1,591#2–21
2Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5211,495–1,546#4–20
3Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,5121,482–1,543#9–57
4gpt-5.5-highopenaisept. 2026$5 / $301,5041,483–1,526#9–34
5Claude Opus 5 (High)anthropicsept. 2026$5 / $251,5041,483–1,525#5–11
6Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,5041,478–1,529#2–29
7Gemini 3 Progoogleian. 2026—1,5031,474–1,533#23–90
8Kimi K3 (Max)moonshotiun. 2026$0.25 / $11.941,5031,477–1,529#10–39
9Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,4991,478–1,520#2–25
10Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,4961,479–1,514#9–36
11gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4951,469–1,521#6–25
12Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,4921,455–1,529#13–33
13Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,4891,465–1,513#1–18
14gemini-3-flashgoogleian. 2026—1,4881,454–1,522#38–153
15qwen3.5-max-previewalibabaoct. 2026—1,4841,440–1,528#33–77
16gpt-5.4-highopenaisept. 2026$2.50 / $151,4791,455–1,504#12–29
17gemini-3.5-flash-highgooglesept. 2026$1.50 / $91,4791,455–1,503#10–26
18gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4771,452–1,503#16–95
19grok-4.20-beta1xaioct. 2026—1,4761,436–1,516#46–119
20qwen3.8-maxalibabaoct. 2026$2 / $61,4751,446–1,503#12–40
21gpt-5.6-terra-xhighopenaisept. 2026$2 / $121,4751,449–1,500#13–59
22Muse Spark 1.1metasept. 2026$1.25 / $4.251,4671,443–1,491#21–115
23glm-5.3-maxzaiaug. 2026$0.08 / $11,4641,433–1,494#18–52
24gpt-5.5-instantopenaisept. 2026—1,4631,426–1,500#52–114
25gpt-5.1-highopenainov. 2025$1.25 / $101,4601,433–1,488#45–242
26claude-opus-4-8anthropicsept. 2026$5 / $251,4591,438–1,481#15–33
27deepseek-v4-prodeepseekaug. 2026$0.66 / $1.981,4561,432–1,479#17–54
28glm-5.2-maxzaiiun. 2026$0.62 / $2.421,4551,432–1,478#9–49
29gpt-6-sol-maxopenaioct. 2026$2 / $101,4481,408–1,489#7–53
30gpt-5.2-chat-latest-20260210openaifeb. 2026—1,4481,412–1,484#44–72
31claude-opus-4-5-20251101-high-32kanthropicnov. 2025—1,4471,416–1,478#36–94
32gemini-3.5-flash-litegoogleoct. 2026$0.30 / $2.501,4461,419–1,472#62–171
33deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,4451,408–1,483#23–31
34claude-sonnet-5-highanthropicsept. 2026$2 / $101,4451,421–1,469#24–58
35grok-4.5xaisept. 2026$2 / $61,4441,416–1,471#29–70

Se afișează Japoneză 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.