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: GPT-6 Sol Scales Near-Linearly With Effort but Lags in Bug Hunt(2 posts)→
More from Models
- Claude Opus 5.5 shown handling a code review, 'taking Theo's job' for the day — 0xkarasy · 2026-09-23
- Sarvam's Saaras V4 adds keyterm prompting to boost speech transcription accuracy — cneuralnetwork · 2026-09-23
- Xiaomi's MiMo V2.6 Pro tops open-source leaderboard at ~$0.13 per task — heyshrutimishra · 2026-09-23
- Xiaomi MiMo V2.6 Pro tops open-source leaderboard at 46, costs ~$0.13 per task — heyshrutimishra · 2026-09-23
- Deep-scan reveals Muse agent's hidden powers: Instagram DMs, HomeKit control, its own email identity — flaneur451 · 2026-09-23
- Yacine on Chinese RL SOTA models: it's just on-policy synthetic data — yacineMTB · 2026-09-23