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
9 min
Toate sursele se sincronizează normal
  • Arena · Textacum 9 ore
  • Arena · WebDevacum 9 ore
  • Arena · Visionacum 9 ore
  • Arena · Agentacum 9 ore
  • GPQA Diamondacum 9 minute
  • SWE-benchacum 9 minute
  • Terminal-Benchacum 9 minute
  • ARC-AGI-2acum 9 minute

claude-fable-5

1,499±8

1,491CI1,507

anthropicsept. 2026oscilație #4–#20

Document Arena ×138 din 38 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1claude-fable-5anthropicsept. 2026$10 / $501,4991,491–1,507#4–20
2claude-opus-4-6-highanthropicsept. 2026$5 / $251,4951,489–1,502#2–25
3claude-opus-4-7anthropicsept. 2026$5 / $251,4941,488–1,501#1–18
4claude-fable-5.1-maxanthropicsept. 2026$10 / $501,4931,478–1,508#2–21
5claude-opus-5-highanthropicsept. 2026$5 / $251,4901,483–1,497#5–11
6gpt-5.6-sol-xhighopenaisept. 2026$4 / $201,4891,480–1,498#6–25
7claude-opus-4-8-highanthropicsept. 2026$5 / $251,4861,479–1,493#15–33
8gpt-5.5openaisept. 2026$5 / $301,4831,476–1,489#9–34
9muse-spark-1.1metasept. 2026$1.25 / $4.251,4791,471–1,488#21–115
10claude-sonnet-4-6anthropicsept. 2026$3 / $151,4781,472–1,484#38–77
11gpt-5.6-terra-xhighopenaisept. 2026$2 / $121,4771,468–1,485#13–59
12claude-sonnet-5-highanthropicsept. 2026$2 / $101,4761,468–1,483#24–58
13gpt-6-astra-maxopenaisept. 2026$10 / $501,4731,458–1,487#1–18
14gpt-5.4openaisept. 2026$2.50 / $151,4701,464–1,476#12–29
15muse-spark-1.3-maxmetasept. 2026$1.25 / $4.251,4681,450–1,486#13–33
16muse-sparkmetasept. 2026—1,4671,449–1,486#16–40
17claude-opus-4-5-20251101anthropicnov. 2025$5 / $251,4651,454–1,475#20–62
18grok-4.5xaisept. 2026$2 / $61,4641,456–1,473#29–70
19gpt-5.6-luna-xhighopenaisept. 2026$0.20 / $1.201,4621,454–1,470#30–146
20grok-4.6-highxaisept. 2026$2 / $61,4611,449–1,473#15–52
21gemini-3.5-flash-mediumgooglesept. 2026$1.50 / $91,4611,453–1,468#10–26
22gpt-5.5-instantopenaisept. 2026—1,4601,452–1,469#52–114
23gemini-3.1-pro-previewgooglesept. 2026$2 / $121,4591,454–1,464#9–36
24gemini-3.6-flash-highgooglesept. 2026$0.75 / $3.751,4531,443–1,464#16–95
25qwen3.7-plusalibabasept. 2026$0.32 / $1.281,4531,443–1,462#51–124
26gemini-3-progoogleian. 2026—1,4511,442–1,460#23–90
27kimi-k2.6moonshotapr. 2026$0.65 / $3.411,4501,442–1,458#29–78
28claude-sonnet-4-5-20250929anthropicsept. 2025$3 / $151,4491,443–1,455#66–232
29gemma-4-31bgooglemar. 2026—1,4451,437–1,452#63–214
30grok-4.20-beta-0309-reasoningxaisept. 2026—1,4391,432–1,447#49–207
31gemini-3-flashgoogleian. 2026—1,4391,430–1,449#38–153
32kimi-k2.5-thinkingmoonshotsept. 2026—1,4361,429–1,443#68–225
33minimax-m3minimaxiun. 2026$0.30 / $1.201,4331,425–1,441#50–264
34gemini-2.5-progoogleiun. 2025$1.25 / $101,4311,424–1,437#60–432
35gpt-5.2openaidec. 2025$1.75 / $141,4251,419–1,431#34–92

Se afișează Document 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.