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
- China’s AI arms race is increasingly defined by chips, data centers, and open models — BenBajarin · 2026-07-22
- Google says its most ambitious pre-training run yet has started for Gemini 4 — andrew_n_carr · 2026-07-22
- Sam Altman is headed to Washington to brief Congress on OpenAI’s GPT-6 line — inductionheads · 2026-07-22
- Benchmark chart pits GPT-5.6 Luna, Grok 4.5 and Gemini 3.6 Flash on price and scores — iruletheworldmo · 2026-07-22
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gemini 3.6 Flash is now available in Antigravity and chat — MartianOnJupiter · 2026-07-22