Claude Code vs. Codex
Comparison between Claude Code and Codex across the Artificial Analysis Coding Agent Index, including benchmark scores, cost, execution time, and token usage.
For details relating to our methodology, see our methodology page.
Explore other comparisons
vs
Highlights
Comparison
Side-by-side comparison of Claude Code and Codex.
Coding Agent Comparison
Metric |  Claude CodeFable 5.1 (max) (with fallback) |  CodexGPT-6 Astra (max) | Analysis |
|---|---|---|---|
Agent Harness | Claude Code | Codex | |
Representative Model | Fable 5.1 (max) (with fallback) | GPT-6 Astra (max) | |
Coding Agent Index | 62 | 62 | Claude Code has a higher Coding Agent Index than Codex |
DeepSWE v1.1 | 64% | 68% | Codex has a higher DeepSWE v1.1 score than Claude Code |
Terminal-Bench 4.0 | 58% | 56% | Claude Code has a higher Terminal-Bench 4.0 score than Codex |
SWE-Atlas-QnA | 65% | 62% | Claude Code has a higher SWE-Atlas-QnA score than Codex |
Cost per Task | $12.39 | $7.47 | Codex has a lower cost per task than Claude Code |
Time per Task | 34.8m | 29.4m | Codex has a lower time per task than Claude Code |
Turns per Task | 36.7 | 39.4 | Claude Code has a lower turns per task than Codex |
Token Usage per Task | 5.7M | 3.3M | Codex has a lower token usage per task than Claude Code |
Cache Hit Rate | 92% | 93% | Codex has a higher cache hit rate than Claude Code |
Model Variants
Evaluated model variants for Claude Code and Codex.
Model Variants
| Claude Code | Fable 5.1 (max) (with fallback) | 62 | 64% | 58% | 65% | $12.39 | 34.8m | 5.7M |
| Claude Code | Opus 5 (max) | 60 | 63% | 55% | 62% | $10.79 | 41.9m | 11.4M |
| Claude Code |  Qwen3.8 Max | 43 | 51% | 17% | 62% | $3.48 | 1.1h | 8.7M |
| Codex | GPT-6 Astra (max) | 62 | 68% | 56% | 62% | $7.47 | 29.4m | 3.3M |
| Codex | GPT-6 Sol (max) | 57 | 69% | 43% | 58% | $2.99 | 22.3m | 9.8M |
| Codex | GPT-5.6 Sol (max) | 55 | 72% | 37% | 54% | $6.35 | 20.6m | 10.2M |
| Codex | GPT-5.6 Luna (max) | 43 | 66% | 15% | 49% | $0.44 | 23.5m | 14.9M |
| Codex |  DeepSeek V4 Pro 0813 (max) | 43 | 57% | 10% | 62% | $0.24 | 40.3m | 24.2M |
| Codex | GPT-6 Luna (max) | 41 | 64% | 15% | 44% | $0.18 | 21.4m | 10.2M |
| Codex | DeepSeek V4 Flash 0731 (max) | 39 | 54% | 11% | 51% | $0.09 | 18.3m | 15.4M |
Performance
Performance across the Artificial Analysis Coding Agent Index.
Artificial Analysis Coding Agent Index
Artificial Analysis Coding Agent Index v1.5 incorporates 3 benchmarks: DeepSWE v1.1, Terminal-Bench 4.0, and SWE-Atlas-QnA · Higher is better
Color by
Artificial Analysis Coding Agent Index vs. Cost per Task
Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD)
Color by
Most attractive quadrant
Pareto line
Token Usage
Token consumption across the Artificial Analysis Coding Agent Index.
Token Usage per Task
Average input, cache, and output tokens per task
Prompt cache hit rates can vary significantly by provider routing, which can materially change effective cost.
Artificial Analysis Coding Agent Index vs. Total Tokens
Artificial Analysis Coding Agent Index vs. average total tokens per task
Color by
Most attractive quadrant
Cost
Pay-per-token API cost across the Artificial Analysis Coding Agent Index, based on current per-token pricing.
Cost per Task
Average pay-per-token API cost per task (USD) · Lower is better
Color by
Execution Time
Active agent runtime across the Artificial Analysis Coding Agent Index.
Time per Task
Average agent wall time per task · Lower is better
Color by
Artificial Analysis Coding Agent Index vs. Execution Time
Artificial Analysis Coding Agent Index vs. average agent wall time per task
Color by
Most attractive quadrant