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
10 min
Toate sursele se sincronizează normal
  • Arena · Textacum 9 ore
  • Arena · WebDevacum 9 ore
  • Arena · Visionacum 9 ore
  • Arena · Agentacum 9 ore
  • GPQA Diamondacum 10 minute
  • SWE-benchacum 10 minute
  • Terminal-Benchacum 10 minute
  • ARC-AGI-2acum 10 minute
FrontierMath ×169 din 69 modele
ModelOrganizație± CIOscilațieAdaugă la comparație
1gpt-5.5-pro-pre-releaseOpenAI——52.4%49.5%–55.3%#23–60
2gpt-5.5-pre-releaseOpenAI——51.7%48.8%–54.6%#22–36
3gpt-5.4-pro-2026-03-05OpenAImar. 2026$30 / $18050.0%47.1%–52.9%#20–171
4gpt-5.4-2026-03-05OpenAIsept. 2026$2.50 / $1547.6%44.7%–50.5%#12–29
5claude-opus-4-8Anthropicsept. 2026$5 / $2547.2%44.3%–50.2%#15–33
6claude-opus-4-7Anthropicsept. 2026$5 / $2543.8%40.9%–46.7%#1–18
7claude-opus-4-6Anthropicsept. 2026$5 / $2540.7%37.8%–43.6%#2–25
8gpt-5.2-2025-12-11OpenAIdec. 2025$1.75 / $1440.7%37.8%–43.6%#34–92
9muse-sparkMeta AIsept. 2026—39.0%36.1%–41.9%#16–40
10gemini-3.5-flashGoogle DeepMindsept. 2026$1.50 / $939.0%36.1%–41.8%#10–26
11kimi-k2.6Moonshotapr. 2026$0.65 / $3.4139.0%36.1%–41.8%#29–78
12gemini-3-pro-previewGoogle DeepMind——37.6%34.8%–40.4%#19–120
13gemini-3.1-pro-previewGoogle DeepMindsept. 2026$2 / $1236.9%34.1%–39.7%#9–36
14gemini-3-flash-previewGoogle DeepMind—$0.50 / $335.6%32.8%–38.5%#27–99
15glm-5.1Z.ai (Zhipu AI)apr. 2026$0.97 / $3.0433.4%30.7%–36.2%#44–75
16gpt-5-2025-08-07OpenAIaug. 2025$1.25 / $1032.4%29.7%–35.2%#64–149
17claude-sonnet-4-6Anthropicsept. 2026$3 / $1532.4%29.6%–35.2%#38–77
18gpt-5.1-2025-11-13OpenAInov. 2025$1.25 / $1031.0%28.3%–33.8%#45–242
19gemini-2.5-deep-think-2025-08-01-webappGoogle,Google DeepMind——29.0%26.3%–31.7%—
20gpt-5.4-mini-2026-03-17OpenAIoct. 2026$0.75 / $4.5028.3%26.2%–30.3%#75–180
21fireworks/kimi-k2p5Moonshot——27.9%25.3%–30.5%#80–115
22gpt-5-mini-2025-08-07OpenAIaug. 2025$0.25 / $227.2%24.6%–29.9%#126–343
23qwen3.6-plusAlibabaoct. 2026$0.33 / $1.9526.2%23.6%–28.8%#47–265
24gpt-5.4-nano-2026-03-17OpenAIoct. 2026$0.20 / $1.2525.9%23.3%–28.4%#95–222
25o4-mini-2025-04-16OpenAIapr. 2025$1.10 / $4.4024.8%22.3%–27.4%#129–274
26qwen3.6-max-previewAlibabaoct. 2026—23.1%20.6%–25.6%#34–53
27fireworks/deepseek-v3p2DeepSeek——22.1%18.0%–26.2%—
28moonshotai/Kimi-K2-ThinkingMoonshot——21.4%19.0%–23.8%—
29qwen3.5-plusAlibabafeb. 2026$0.30 / $1.8021.0%18.6%–23.4%#106–403
30claude-opus-4-5-20251101Anthropicnov. 2025$5 / $2520.7%18.3%–23.1%#20–62
31grok-4-0709xAIiul. 2025—19.7%17.3%–22.0%#95–276
32o3-2025-04-16OpenAIapr. 2025$2 / $818.7%16.4%–21.0%#79–318
33glm-5Z.ai (Zhipu AI)feb. 2026$1 / $3.2016.4%14.2%–18.6%#57–153
34claude-sonnet-4-5-20250929Anthropicsept. 2025$3 / $1515.2%13.1%–17.3%#66–232
35gemini-2.5-proGoogle DeepMindiun. 2025$1.25 / $1014.1%12.1%–16.2%#60–432

Se afișează FrontierMath 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.