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
16 min
Toate sursele se sincronizează normal
  • Arena · Textacum 12 ore
  • Arena · WebDevacum 12 ore
  • Arena · Visionacum 12 ore
  • Arena · Agentacum 12 ore
  • GPQA Diamondacum 16 minute
  • SWE-benchacum 16 minute
  • Terminal-Benchacum 16 minute
  • ARC-AGI-2acum 16 minute
Matematică ×1380 din 380 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1Gemini 4 Argon (High)googleoct. 2026$2 / $101,5291,494–1,563#1–10
2Claude Fable 5.1 (Max)anthropicsept. 2026$10 / $501,5251,504–1,547#2–21
3Claude Fable 5 (High)anthropicsept. 2026$10 / $501,5231,510–1,536#4–20
4Gemini 3.8 Flash (High)googleoct. 2026$0.83 / $4.131,5221,508–1,536#2–29
5Claude Opus 5 (High)anthropicsept. 2026$5 / $251,5221,511–1,533#5–11
6Claude Opus 4.6 (High)anthropicsept. 2026$5 / $251,5181,508–1,527#2–25
7glm-5.3-flashzaiaug. 2026$0.05 / $0.201,5061,491–1,521#26–60
8Gemini 3.7 Flash (High)googleoct. 2026$0.75 / $3.751,5061,490–1,522#9–57
9Muse Spark 1.3 (Max)metasept. 2026$1.25 / $4.251,5041,484–1,524#13–33
10Claude Opus 4.7 (High)anthropicsept. 2026$5 / $251,5041,493–1,514#1–18
11gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,5021,488–1,517#16–95
12Claude Opus 5.5 (High)anthropicoct. 2026$4 / $201,5021,474–1,530#2–11
13claude-sonnet-5.5-xhighanthropicoct. 2026$2 / $101,5021,471–1,533#4–26
14Kimi K3 (Max)moonshotiun. 2026$0.28 / $11.941,5011,485–1,516#10–39
15gpt-5.5openaisept. 2026$5 / $301,5011,490–1,511#9–34
16qwen3.8-maxalibabaoct. 2026$2 / $61,5001,484–1,515#12–40
17gemini-3.5-flash-highgooglesept. 2026$1.50 / $91,4971,484–1,509#10–26
18Muse Spark 1.1metasept. 2026$1.25 / $4.251,4961,482–1,509#21–115
19gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4961,482–1,509#6–25
20deepseek-v4.1-flash-maxdeepseekoct. 2026$0.15 / $0.601,4941,472–1,517#23–31
21glm-5.3-maxzaiaug. 2026$0.08 / $1.401,4941,476–1,513#18–52
22gpt-6.1-sol-maxopenaioct. 2026$2 / $101,4941,463–1,525#1–15
23claude-opus-4-8-highanthropicsept. 2026$5 / $251,4941,483–1,505#15–33
24gpt-5.4-highopenaisept. 2026$2.50 / $151,4911,480–1,502#12–29
25Gemini 3.1 Pro Previewgooglesept. 2026$2 / $121,4881,480–1,496#9–36
26mimo-v2.6-proxiaomisept. 2026$0.43 / $0.871,4881,448–1,528#18–64
27gpt-6-astra-maxopenaisept. 2026$10 / $501,4861,463–1,510#1–18
28qwen3.7-max-previewalibabaoct. 2026—1,4861,447–1,524#29–73
29glm-5.2-maxzaiiun. 2026$0.62 / $2.421,4851,473–1,498#9–49
30Muse Spark 1.2 (xHigh)metaoct. 2026$1.25 / $4.251,4841,456–1,512#13–112
31gpt-5.6-terra-xhighopenaisept. 2026$2 / $121,4801,467–1,494#13–59
32mimo-v2.5-proxiaomiapr. 2026$0.43 / $0.871,4801,470–1,490#40–129
33kimi-k2.6moonshotapr. 2026$0.65 / $3.411,4791,466–1,492#29–78
34hy3tencentiul. 2026$0.08 / $0.331,4781,456–1,501#65–318
35gpt-5.6-luna-xhighopenaisept. 2026$0.20 / $1.201,4781,464–1,492#30–146

Se afișează Matematică 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.