GPT-6 Sol/Luna Benchmarks Leak: ~85% Cheaper Per Task Than Fable 5.1
kimmonismus · x · 2026-09-23
kimmonismus shares benchmark and cost numbers for GPT-6 Sol and Luna:
- FrontierCode: Sol hits 48.4% vs Fable 5.1's 48.7% (both xhigh), at $1.37 vs $9.27 per task — roughly 85% cheaper
- DeepSWE: 68.8% (max) vs Fable 5's best 69.9% (xhigh), $2.74 vs $13.41 per task, 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 per task
The takeaway: the GPT-6 generation matches near-flagship performance on agentic/coding tasks at a fraction of the per-task cost.
More from Models
- MKA benchmark blog: how agents are graded on visual professional deliverables — patloeber · 2026-11-12
- New MKA benchmark: Claude Opus 4.5 tops 21 models at 57% on visual knowledge work — patloeber · 2026-11-12
- Google's Physical-Engineering's Last Exam: all 14 frontier models score below 50% — dl_weekly · 2026-11-12
- Commit leak reveals unreleased Gemini 4 variants: Argon, Hydrogen and Helix (unconfirmed) — BlackHC · 2026-11-11
- Rewiring just 89 of 442,368 neurons in Qwen3-8B matches full SFT for a persona — maxsloef · 2026-11-11
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-11