Bug Hunt chart: score vs subscription cost, Gemini 4 Neon xhigh tops at 63 for $1.80
PawelHuryn · x · 2026-11-20
A companion chart from Paweł Huryn's Bug Hunt Benchmark plots score against subscription-adjusted run cost across 28 runs of six models at every effort level:
- The "cheap and strong" corner includes GPT-6.2 Sol high/max, Gemini 4 Neon xhigh, and GPT-6.2 Astra tiers
- Gemini 4 Neon xhigh scores 63 for $1.80; Astra max 62.7 for $2.77; Fable 5.2 max hits 58 but costs $5.12
- Opus 5.5 and Grok 4.7 cluster in the lower-right, poor value
Huryn notes Gemini 4 Neon would be an ideal candidate if Google allowed running it from other harnesses (allegedly in progress); doing so currently breaks Google's terms.
More from coding & agent
- Measured: Claude Max delivers 46.4x API value on Opus 5.5, beating ChatGPT Pro's 10.25x — PawelHuryn · 2026-11-20
- 10 open-source GitHub repos that turn your docs into queryable knowledge graphs — victor_explore · 2026-11-20
- What happens when two AI agents disagree? The multi-agent conflict problem — EricJose59 · 2026-11-20
- AI turns Mediterranean illustration into interactive 3D world; Three.js wall-crash demo costs $6.98 — Saboo_Shubham_ · 2026-11-20
- Higgsfield launches GPU Harness: rent GPUs inside Claude and ChatGPT to render and train LoRAs — CurieuxExplorer · 2026-11-20
- GitHub adds reachability analysis to Dependabot alerts to prioritize real vulnerability risk — 0xkarasy · 2026-11-20