GPT-6 Sol scales almost linearly with effort level, still trails Opus 5.5 in tests
PawelHuryn · x · 2026-09-23
Developer Pawel Huryn shares live-benchmark comparisons across GPT-6 Sol effort levels (n=3 for max, n=1 otherwise), showing scores rise in an almost straight line with effort. Earlier data points: GPT-6 Sol (max) ≈ GPT-5.6 Sol (medium), but still below Opus 5.5 (medium). GPT-6 Luna and Terra are queued up next for testing.
Related event: Tests Show GPT-6 Sol Scales Nearly Linearly With Effort(3 posts)→
More from Models
- DeepMind launches AlphaGenome 2 with major performance leap in variant-effect prediction — anshulkundaje · 2026-11-11
- US data vendors accused of selling RL environments to Chinese military-linked firms — xeophon · 2026-11-11
- Theory: Typos Disrupt LLM Tokenization, Which May Explain Why AI Text Has a Distinct Smell — menhguin · 2026-11-11
- LMArena co-founder explains AI evaluation methodology and policy in new podcast — MattPerault · 2026-11-11
- Runway open-sources Praxis-1, turning video pretraining into real robot control — runwayml · 2026-11-11
- DeepMind launches AlphaGenome 2, spotting nearly 2x more gene-regulating mutations — GoogleDeepMind · 2026-11-11