← Back to dashboard
OpenAI·Code — weighted competency·Tue 2 Jun 2026

GPT-5 Code

GPT-5 Code scores 79/100 competency for Code at $14.00.

Low confidenceCloud · API
Competency
79/100
category rank #2
Cost
$14.00/ 1M tokens
blended
Speed
74/100
Moderate
Accuracy
2.4% halluc.
High confidence

Score history.

Weighted Code competency · last 12 weeks · weekly snapshot.

79/100
— flat
79

What it's actually good at.

Score on each business-task subset that goes into the weighted competency.

Test Generation10% of category weight
87
Code Generation40% of category weight
75
Review & Bug Fixing30% of category weight
79
Full-Repo Understanding20% of category weight
83

Best for. Watch out for.

✓ Best for
  • Strong at Code Generation for OpenAI.
  • Strong at Review & Bug Fixing for OpenAI.
⚠ Watch out for
  • Validate fit for your specific workload before committing.

Pricing.

Published usage pricing. Figures refresh daily from our pricing sources.

$14.00

Usage pricing

$14.00/1M tok
Input
$14.00 / 1M tokens
Output
$42.00 / 1M tokens

Where it sits.

Position against the rest of the category. Ranked by weighted competency.

RankModelScoreCostSpeedΔ vs GPT-5
01GPT-5 Code79$14.0074 / 100
02DeepSeek V3.1 Coder64$0.676 / 100-16
03Qwen 3 Coder48$1.4078 / 100-32