From the archive. Prices, rankings and availability are as of Jun 22, 2026.
Best Model for Coding Right Now
The tracked frontier spans 28 Elo points on coding, but input prices run 4x and output prices 12x. Here is how helloai's scoring picks a winner for engineering work — and when to trade rank for cost.
If you ask helloai's /api/recommend for coding today, Claude Opus 4.8 wins — but not by the margin the leaderboard alone suggests. The tracked set spans just 28 Elo points from Opus 4.8 at 1503 down to Qwen3.7-Max at 1475, yet input pricing runs from $1.25 per million tokens for Grok 4.3 to $5 for Opus 4.8 and GPT-5.5. Output spreads are wider: $2.50 for Grok against $30 for GPT-5.5. The engine weights category fit at 40 percent, Elo 35, cost 15, context 10. Opus 4.8 is the Coding and Engineering leader and carries the benchmark story — 88.6 percent on SWE-bench Verified, 69.2 on Pro — so it tops the stack for the default answer with no budget constraint.
The interesting split is what happens when cost enters the picture. Qwen3.7-Max scores second for coding: it lists Coding and Engineering among its strengths, sits ten Elo points below Opus, and prices at roughly $2.50 input and $7.50 output — half the input cost of the closed flagships and a fraction of GPT-5.5's output rate. Its 80.4 percent on SWE-bench Verified is real, and it has documented 35-hour multi-agent runs. That gap compounds faster than a ten-point Elo deficit in agent loops that burn output tokens. Grok 4.3 ranks lower on pure coding fit but at $1.25/$2.50 is the cheapest tracked frontier option for high-volume drafts and test scaffolding.
GPT-5.5 sits in an awkward middle. It posts strong agentic numbers — 82.7 percent on Terminal-Bench 2.0 and 73.1 percent on Expert-SWE — and matches Opus on input price at $5, but its $30 output rate is the highest in the set. The engine penalizes that on cost-weighted tasks unless you filter it in for provider reasons. Gemini 3.1 Pro is not a coding specialist in our taxonomy; it leads Hard Reasoning and Science, and it will not top a coding query even at $2/$12 unless your pipeline is multimodal or reasoning-heavy.
Practical routing: reach for Opus 4.8 when the job is codebase-scale — migrations, parallel subagent workflows, or SWE-bench Pro-class problems. Switch to Qwen3.7-Max when you need sustained agentic execution and can accept a slightly lower rank for half the bill. Use Grok 4.3 as a cost firewall for iterative work that humans gate before merge. Reserve GPT-5.5 for terminal-native agent stacks where Terminal-Bench-shaped tool chains are the bottleneck and output cost is a rounding error. None require chasing a bigger Elo number; the frontier is already a near-tie.
Coding procurement in mid-2026 has decoupled from the leaderboard. Nineteen to twenty-eight Elo points separate the models developers ship, while economics and task shape diverge by an order of magnitude. The honest workflow is to call /api/recommend?task=coding with your real budget and context constraints, then override only when you know your pipeline's shape — terminal agents, multimodal inputs, or subagent orchestration — that the generic weights underweight. The best model for coding is not the highest score; it is the one whose price and behavior match how your agents run overnight.