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
29 min
Toate sursele se sincronizează normal
  • Arena · Textacum 29 de minute
  • Arena · WebDevacum 29 de minute
  • Arena · Visionacum 29 de minute
  • Arena · Agentacum 29 de minute
  • GPQA Diamondacum 53 de minute
  • SWE-benchacum 53 de minute
  • Terminal-Benchacum 53 de minute
  • ARC-AGI-2acum 53 de minute
Programare ×1391 din 391 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Gemini 4 Argon (High)googleoct. 2026$2 / $101,5591,542–1,576#1–10
2Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5511,544–1,557#4–20
3Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,5511,545–1,556#1–18
4Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,5481,543–1,554#2–25
5Muse Wonder (Max)metaoct. 2026—1,5481,527–1,569#14–56
6Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5481,534–1,561#2–11
7gpt-6-astra-maxopenaisept. 2026$10 / $501,5431,532–1,555#1–18
8gpt-6.1-sol-maxopenaioct. 2026$2 / $101,5401,523–1,557#1–15
9Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,5391,526–1,552#13–112
10Kimi K3 (Max)moonshotiun. 2026$0.25 / $11.941,5381,531–1,545#10–39
11mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,5381,520–1,555#18–64
12Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,5371,526–1,549#2–21
13Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,5351,526–1,544#13–33
14gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,5341,527–1,541#6–25
15claude-opus-4-8-highanthropicsept. 2026$5 / $251,5341,528–1,539#15–33
16Claude Opus 5 (High)anthropicsept. 2026$5 / $251,5331,527–1,539#5–11
17Muse Spark 1.1metasept. 2026$1.25 / $4.251,5331,526–1,539#21–115
18claude-opus-4-5-20251101-high-32kanthropicnov. 2025—1,5311,523–1,538#36–94
19claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,5301,515–1,545#4–26
20Muse Sparkmetasept. 2026—1,5291,519–1,539#16–40
21claude-sonnet-4-6anthropicsept. 2026$3 / $151,5281,523–1,534#38–77
22Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,5281,521–1,535#2–29
23glm-5.3-flashzaiaug. 2026$0.05 / $0.201,5251,517–1,532#26–60
24qwen3.7-max-previewalibabaoct. 2026—1,5241,506–1,542#29–73
25deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,5231,513–1,534#23–31
26qwen3.8-maxalibabaoct. 2026$2 / $61,5231,516–1,531#12–40
27claude-opus-4-5-20251101anthropicnov. 2025$5 / $251,5231,517–1,528#20–62
28mimo-v2.5-proxiaomiapr. 2026$0.43 / $0.871,5221,516–1,527#40–129
29Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,5211,517–1,526#9–36
30gpt-5.4-highopenaisept. 2026$2.50 / $151,5201,515–1,526#12–29
31claude-sonnet-5-highanthropicsept. 2026$2 / $101,5201,514–1,526#24–58
32claude-sonnet-4-5-20250929-high-32kanthropicsept. 2025—1,5191,514–1,524#59–261
33gpt-5.5-highopenaisept. 2026$5 / $301,5191,513–1,524#9–34
34glm-5.3-maxzaiaug. 2026$0.08 / $1.401,5191,510–1,527#18–52
35gpt-6-sol-maxopenaioct. 2026$2 / $101,5181,507–1,530#7–53

Se afișează Programare 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.