GPT-6.1 Sol nearly matches flagship on 105 planted bugs, at ~1/5 the cost
PawelHuryn · x · 2026-09-30
- Pawel Huryn planted 105 bugs across 2 real repos and let models find and fix them, publishing max-tier results:
- GPT-6 Astra: 45 fixed for $33
- GPT-6.1 Sol: 44 fixed for just $6.56
- GPT-5.6 Sol: 43.5 fixed for $95.35
- Opus 5.5: 41.7 fixed for $58.53
- GPT-6 Sol: 29.3 fixed for $9.33
- He concludes GPT-6.1 Sol is a genuine upgrade, unlike GPT-6 Sol which he calls "just a nerfed GPT-5.6 Terra."
- Takeaway: near-flagship coding performance at roughly one-fifth the cost, with lower-tier results still pending.
More from Models
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Stealth Anthropic model spotted in Devin build as METR chart shows frontier pace up 1.4x — daniel_mac8 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16
- METR time-horizon chart updated: doubling every 1.7 months since Opus 4.5, 'Model 4' ~38h — ben_j_todd · 2026-11-16