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
Spaniolă ×1282 din 282 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5031,469–1,537#2–11
2Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5031,486–1,520#4–20
3Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,5011,474–1,528#2–21
4Claude Opus 4.6anthropicsept. 2026$5 / $251,4991,487–1,512#2–25
5Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,4991,484–1,513#1–18
6Gemini 4 Argon (High)googleoct. 2026$2 / $101,4971,459–1,536#1–10
7Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,4951,460–1,530#13–112
8Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,4931,467–1,519#13–33
9Claude Opus 5 (Max)anthropicsept. 2026$5 / $251,4871,467–1,507#5–11
10gpt-5.5-instantopenaisept. 2026—1,4861,464–1,508#52–114
11Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,4851,464–1,506#9–57
12Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,4831,472–1,494#9–36
13claude-opus-4-8-highanthropicsept. 2026$5 / $251,4801,465–1,495#15–33
14Muse Sparkmetasept. 2026—1,4791,453–1,506#16–40
15glm-5.2-maxzaiiun. 2026$0.62 / $2.421,4781,462–1,494#9–49
16Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,4781,461–1,496#2–29
17Kimi K3 (Max)moonshotiun. 2026$0.30 / $11.941,4781,460–1,497#10–39
18qwen3.8-maxalibabaoct. 2026$2 / $61,4781,457–1,499#12–40
19gemini-3-flashgoogleian. 2026—1,4781,459–1,497#38–153
20claude-opus-4-5-20251101-high-32kanthropicnov. 2025—1,4761,459–1,494#36–94
21gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4761,456–1,496#16–95
22Muse Spark 1.1metasept. 2026$1.25 / $4.251,4751,458–1,492#21–115
23glm-5.3-flashzaiaug. 2026$0.05 / $0.201,4751,458–1,493#26–60
24hy3tencentiul. 2026$0.08 / $0.331,4741,447–1,502#65–318
25gpt-5.2-chat-latest-20260210openaifeb. 2026—1,4741,456–1,492#44–72
26Gemini 3 Progoogleian. 2026—1,4731,456–1,491#23–90
27gemini-3.5-flash-highgooglesept. 2026$1.50 / $91,4721,456–1,489#10–26
28gpt-6.1-sol-maxopenaioct. 2026$2 / $101,4721,434–1,510#1–15
29gpt-5.5-highopenaisept. 2026$5 / $301,4701,456–1,485#9–34
30ernie-5.0-preview-1203baiduoct. 2026—1,4701,433–1,507#81–216
31dola-seed-2.0-probytedanceoct. 2026—1,4701,457–1,483#52–233
32claude-opus-4-1-20250805anthropicaug. 2025$15 / $751,4681,454–1,481#73–404
33grok-4.20-beta1xaioct. 2026—1,4671,448–1,487#46–119
34glm-5.3-maxzaiaug. 2026$0.08 / $1.401,4671,446–1,489#18–52
35claude-sonnet-4-5-20250929anthropicsept. 2025$3 / $151,4661,454–1,479#66–232

Se afișează Spaniolă 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.