Meta Spark 1.1 Shows Surprisingly Strong Benchmark Performance
Afinetheorem · x · 2026-07-11
On a "vision + geolocation + knowledge" benchmark, the author noted that Meta Spark 1.1 performed surprisingly well:
- Second only to the Gemini 3.x series and Fable
- Even outperforming all OpenAI, Grok, and Chinese models the author has tested
- This task requires mapping locations to latitude and longitude coordinates, representing a challenging visual geographic reasoning task
The author also clarified that using a "hit within 10 miles" standard is necessary because factors like camera focal length make precise localization nearly impossible in some samples.
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- 105 hidden bugs, 2 repos: DeepSeek V4.1 Flash fixes 24 at $1.80 vs Opus 5's 27 at $51.33 — ChartsJournalX · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11