GPT-6 benchmarks: Sol matches Fable 5.1 at ~85% less cost per task
kimmonismus · x · 2026-09-23
kimmonismus compiled GPT-6 Sol/Luna benchmark results alongside pricing (Sol $2/$10, Luna $0.10/$0.50 per 1M input/output tokens).
Sol:
- FrontierCode: 48.4% (xhigh) vs Fable 5.1's 48.7%, $1.37 vs $9.27 per task (85% cheaper).
- DeepSWE: 68.8% (max) vs Fable 5's best 69.9% (xhigh), $2.74 vs $13.41 (80% cheaper).
- AutomationBench: 33.2% (xhigh) vs Fable 5.1 with Opus 5 fallback at 31.4% (max), $0.27 vs at least $2.45.
Luna:
- DeepSWE: 66.6% (max) vs Fable 5's 65.4% (medium), $0.22 vs $6.09 (96% cheaper).
Verdict: Astra-level reliability at a much lower price.
Related event: OpenAI Launches GPT-6 Sol and Luna at Half the Price(47 posts)→
More from Models
- GPT-6's Real Headline: OpenAI Cuts Luna Price in Half to Rival Open Models — dbreunig · 2026-09-23
- Four Models Drop in One Day: GPT-6 Sol, Claude 5.5, Grok 4.7, Xiaomi MiMo-V2.6 — ivan_bezdomny · 2026-09-23
- scaling01 taunts haters after joking Anthropic won't ship Opus 5.5 and Sol today — scaling01 · 2026-09-23
- Unreleased Claude Opus 5.5 SVG demo sparks RL training speculation — adonis_singh · 2026-09-23
- Delip Rao downgrades from $200/mo Google One Ultra to $50 Pro, leaning on local models — deliprao · 2026-09-23
- Why AI progress accelerated: Claude 4.5 kicked off narrow RSI and open-weight catch-up — maksym_andr · 2026-09-23