Inkling 2 Small tops cost-performance frontier at $0.34/task on sudo L7
echen · x · 2026-11-06
Surge AI reports Inkling 2 Small's results on sudo L7, its staff-level software engineering benchmark: $0.34 per task, the cheapest model on the board, scoring within two points of Gemini 4 Argon (7.8× cost, $2.64) and Muse Wonder 1.0 (13× cost, $4.39). It also outscores models costing 3–7× more: Muse Spark 1.3 ($1.85, 5.4×), Gemini 3.8 Flash ($2.47, 7.3×), and GLM 5.3 ($1.15, 3.4×). The chart shows Inkling 2 Small at 14.1, redefining sudo L7's cost-performance frontier.
Related event: Thinking Machines Releases Inkling 2 Small Open-Weight Model(42 posts)→
More from coding & agent
- Google Antigravity rolls out remote agents: tasks run in cloud VMs, approvals via phone — gaganghotra_ · 2026-11-06
- Open-source sprite-gen generates 2D game sprites and animation atlases, smoother GIFs than GPT Image — songguoxiansen · 2026-11-06
- AI revives Facebook's abandoned Prepack, speeding up React renderToString 5.4x — Vjeux · 2026-11-06
- If You're Compute-Constrained, Don't Burn Agent-Compute on Social Agents — nptacek · 2026-11-06
- AI Engineer SH talk: models see the world through their action space, not ours — vincent_koc · 2026-11-06
- teortaxesTex: Singularity still needs bigger models; public AGI easy to dunk on — teortaxesTex · 2026-11-06