Storia in 3 fonti

Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up

Grok 4.5 ranks second on the APEX-SWE leaderboard with 51.2% accuracy, trailing Anthropic's Fable 5 at 65.5% in real-world software engineering tests.

Raccontata da

the-decoder.com

cryptobriefing.com

the-decoder.de

Confronto fonti

3 prospettive sulla stessa storia

AI · summaries

cryptobriefing.comStai leggendo17 g fa

Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up

Grok 4.5 ranks second on the APEX-SWE leaderboard with 51.2% accuracy, trailing Anthropic's Fable 5 at 65.5% in real-world software engineering tests.

originale

the-decoder.com20 g fa

Grok 4.5 is so cheap compared to Fable 5 and GPT 5.5 that benchmark gaps may not matter much

xAI releases Grok 4.5, trained on tens of thousands of Nvidia GB300 GPUs. In coding benchmarks, the model trails Fable 5 and GPT-5.5 but needs 4.2 times fewer tokens than Opus 4.8. At $2 per million input tokens, it…

Leggi questa versione → originale

Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up

Confronto fonti

Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up

Grok 4.5 is so cheap compared to Fable 5 and GPT 5.5 that benchmark gaps may not matter much

Timeline cronologica

Grok 4.5 is so cheap compared to Fable 5 and GPT 5.5 that benchmark gaps may not matter much

Grok 4.5 tops SWE Marathon benchmark as xAI's coding model war heats up

xAI veröffentlicht Grok 4.5: Fast auf Frontier-Niveau, aber deutlich günstiger als die Konkurrenz

xAI veröffentlicht Grok 4.5: Fast auf Frontier-Niveau, aber deutlich günstiger als die Konkurrenz

Grok 4.5 ranks second on APEX-SWE leaderboard as AI coding race heats up

SpaceXAI's Grok 4.5 outperforms GPT-5.6-SOL, challenges AI leaders