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
15 min
Toate sursele se sincronizează normal
  • Arena · Textacum 11 ore
  • Arena · WebDevacum 11 ore
  • Arena · Visionacum 11 ore
  • Arena · Agentacum 11 ore
  • GPQA Diamondacum 15 minute
  • SWE-benchacum 15 minute
  • Terminal-Benchacum 15 minute
  • ARC-AGI-2acum 15 minute
Factuality Arena ×1172 din 172 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Gemini 4 Argon (High)googleoct. 2026$2 / $101,5111,503–1,518#1–10
2Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5091,503–1,516#2–11
3Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,4981,493–1,503#2–21
4Muse Wonder (Max)metaoct. 2026—1,4981,489–1,507#14–56
5Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,4931,490–1,496#2–25
6Claude Opus 5 (Max)anthropicsept. 2026$5 / $251,4891,485–1,493#5–11
7gpt-5.5-highopenaisept. 2026$5 / $301,4861,483–1,489#9–34
8gpt-5.4-highopenaisept. 2026$2.50 / $151,4841,481–1,487#12–29
9mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,4831,475–1,491#18–64
10Claude Fable 5 (High)anthropicsept. 2026$10 / $501,4831,480–1,487#4–20
11Gemini 3 Progoogleian. 2026—1,4811,478–1,485#23–90
12Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,4811,475–1,487#13–112
13qwen3.7-max-previewalibabaoct. 2026—1,4801,471–1,489#29–73
14Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,4791,474–1,483#13–33
15Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,4771,474–1,480#1–18
16gemini-3.5-flash-highgooglesept. 2026$1.50 / $91,4771,474–1,480#10–26
17gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4761,473–1,480#6–25
18Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,4751,471–1,479#9–57
19claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,4741,468–1,481#4–26
20qwen3.5-max-previewalibabaoct. 2026—1,4741,470–1,479#33–77
21Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,4741,470–1,478#2–29
22qwen3.8-maxalibabaoct. 2026$2 / $61,4721,468–1,477#12–40
23Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,4721,470–1,474#9–36
24gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4711,468–1,475#16–95
25Kimi K3 (Max)moonshotiun. 2026$0.30 / $11.941,4711,468–1,475#10–39
26claude-opus-4-8-highanthropicsept. 2026$5 / $251,4701,467–1,473#15–33
27deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,4681,463–1,473#23–31
28gpt-5.6-terra-xhighopenaisept. 2026$2 / $121,4681,464–1,471#13–59
29Muse Sparkmetasept. 2026—1,4681,462–1,473#16–40
30gemini-3-flashgoogleian. 2026—1,4681,464–1,472#38–153
31gpt-6-astra-maxopenaisept. 2026$10 / $501,4661,461–1,472#1–18
32glm-5.3-maxzaiaug. 2026$0.08 / $1.401,4661,461–1,470#18–52
33grok-4.5xaisept. 2026$2 / $61,4661,462–1,469#29–70
34gpt-6.1-sol-maxopenaioct. 2026$2 / $101,4651,458–1,472#1–15
35mimo-v2.5-proxiaomiapr. 2026$0.43 / $0.871,4651,462–1,468#40–129

Se afișează Factuality 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.