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
22.310
Ultima sincronizare
28 min
Toate sursele se sincronizează normal
  • Arena · Textacum 1 oră
  • Arena · WebDevacum 1 oră
  • Arena · Visionacum 1 oră
  • Arena · Agentacum 1 oră
  • GPQA Diamondacum 28 de minute
  • SWE-benchacum 28 de minute
  • Terminal-Benchacum 28 de minute
  • ARC-AGI-2acum 28 de minute

gemini-4-argon

76.0%±1.4%

74.6%CI77.4%

Google DeepMindoct. 2026oscilație #1–#10

gpt-6-astra

75.6%±1.4%

74.2%CI77.0%

OpenAIsept. 2026oscilație #1–#18

gpt-6.1-sol

73.9%±1.4%

72.5%CI75.3%

OpenAIoct. 2026oscilație #1–#15

SimpleQA Verified ×182 din 82 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1gemini-4-argonGoogle DeepMindoct. 2026$2 / $1076.0%74.6%–77.4%#1–10
2gpt-6-astraOpenAIsept. 2026$10 / $5075.6%74.2%–77.0%#1–18
3gpt-6.1-solOpenAIoct. 2026$2 / $1073.9%72.5%–75.3%#1–15
4gemini-3.1-pro-previewGoogle DeepMindsept. 2026$2 / $1273.5%72.1%–74.9%#9–36
5claude-opus-5-5Anthropicoct. 2026$4 / $2072.2%70.8%–73.6%#2–11
6claude-fable-5-1Anthropicsept. 2026$10 / $5070.8%69.4%–72.2%#2–21
7claude-fable-5Anthropicsept. 2026$10 / $5070.7%69.3%–72.1%#4–20
8gemini-3.8-flashGoogle DeepMindoct. 2026$0.83 / $4.1369.7%68.2%–71.2%#2–29
9gpt-5.6-solOpenAIsept. 2026$4 / $2069.7%68.2%–71.2%#6–25
10gemini-3.7-flashGoogle DeepMindoct. 2026$0.75 / $3.7569.2%67.7%–70.7%#9–57
11gemini-3-flash-previewGoogle DeepMind—$0.50 / $366.8%65.3%–68.3%#27–99
12gemini-3.5-flashGoogle DeepMindsept. 2026$1.50 / $966.2%64.7%–67.7%#10–26
13gemini-3.6-flashGoogle DeepMindsept. 2026$0.75 / $3.7566.2%64.7%–67.7%#16–95
14gpt-5.5OpenAIsept. 2026$5 / $3063.0%61.5%–64.5%#9–34
15gpt-6-solOpenAIoct. 2026$2 / $1060.7%59.2%–62.2%#7–53
16muse-spark-1.2Meta AIoct. 2026$1.25 / $4.2560.3%58.7%–61.9%#13–112
17claude-opus-5Anthropicsept. 2026$5 / $2559.9%58.3%–61.5%#5–11
18muse-spark-1.1Meta AIsept. 2026$1.25 / $4.2557.8%56.2%–59.4%#21–115
19Muse-Spark-Open-816B-A42BMeta AI——56.6%55.0%–58.2%#54–119
20grok-4.7xAIoct. 2026$2 / $656.0%54.4%–57.6%#21–72
21qwen3.7-maxAlibabamai 2026$1.48 / $4.4255.8%54.2%–57.3%#41–128
22claude-opus-4-8Anthropicsept. 2026$5 / $2553.0%51.4%–54.6%#15–33
23deepseek-v4-pro-0813DeepSeekaug. 2026$0.66 / $1.9852.9%51.3%–54.5%#40–130
24qwen3.6-max-previewAlibabaoct. 2026—52.0%50.4%–53.6%#34–53
25claude-opus-4-7Anthropicsept. 2026$5 / $2551.7%50.1%–53.3%#1–18
26kimi-k3Moonshotiun. 2026$0.25 / $11.9450.6%49.0%–52.2%#10–39
27gpt-5-2025-08-07OpenAIaug. 2025$1.25 / $1050.1%48.5%–51.7%#64–149
28o3-2025-04-16OpenAIapr. 2025$2 / $849.4%47.8%–51.0%#79–318
29grok-4.6xAIsept. 2026$2 / $649.3%47.7%–50.9%#15–52
30qwen3-max-2025-09-23Alibabasept. 2025—48.7%47.2%–50.3%#81–167
31grok-4.5xAIsept. 2026$2 / $648.3%46.7%–49.9%#29–70
32gpt-5.1-2025-11-13OpenAInov. 2025$1.25 / $1048.0%46.4%–49.6%#45–242
33qwen3.8-max-0902Alibabaoct. 2026$2 / $647.3%45.7%–48.9%#23–155
34claude-opus-4-6Anthropicsept. 2026$5 / $2547.0%45.4%–48.6%#2–25
35deepseek-v4-proDeepSeekaug. 2026$0.66 / $1.9847.0%45.4%–48.6%#17–54

Se afișează SimpleQA Verified 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.