Claude Code vs. Codex

Name: Coding Agent Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

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

Coding Agent Index

Artificial Analysis Coding Agent Index v1.5 · Higher is better

Time per Task

Average agent wall time per task · Lower is better

Cost per Task

Average API cost per task (USD) · Lower is better

Comparison

Side-by-side comparison of Claude Code and Codex.

Coding Agent Comparison

Metric	Claude Code Sonnet 5.5 (max)	Codex GPT-6.1 Sol (xhigh)	Analysis
Agent Harness	Claude Code	Codex
Representative Model	Sonnet 5.5 (max)	GPT-6.1 Sol (xhigh)
Coding Agent Index	68	63	Claude Code has a higher Coding Agent Index than Codex
DeepSWE v1.1	72%	73%	Codex has a higher DeepSWE v1.1 score than Claude Code
Terminal-Bench 4.0	66%	55%	Claude Code has a higher Terminal-Bench 4.0 score than Codex
SWE-Atlas-QnA	67%	61%	Claude Code has a higher SWE-Atlas-QnA score than Codex
Cost per Task	$14.19	$1.04	Codex has a lower cost per task than Claude Code
Time per Task	1.5h	15.5m	Codex has a lower time per task than Claude Code
Turns per Task	265.9	40.1	Codex has a lower turns per task than Claude Code
Token Usage per Task	27.7M	3.2M	Codex has a lower token usage per task than Claude Code
Cache Hit Rate	95%	93%	Claude Code has a higher cache hit rate than Codex

Model Variants

Evaluated model variants for Claude Code and Codex.

Model Variants


Claude Code	Sonnet 5.5 (max)	68	72%	66%	67%	$14.19	1.5h	27.7M
Claude Code	Opus 5.5 (max)	66	68%	63%	66%	$13.04	1.1h	15.6M
Claude Code	Sonnet 5.5 (xhigh)	63	68%	58%	62%	$3.33	27.0m	7.1M
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	Sonnet 5.5 (high)	55	67%	42%	56%	$1.24	12.3m	2.7M
Claude Code	Step 5 Preview	51	62%	33%	58%	$1.66	56.4m	21.7M
Claude Code	Sonnet 5.5 (medium)	46	65%	27%	45%	$0.62	8.5m	1.3M
Claude Code	Qwen3.8 Max	43	51%	17%	62%	$3.48	1.1h	8.7M
Claude Code	Sonnet 5.5 (low)	42	62%	25%	39%	$0.48	6.3m	977.3K
Claude Code	Haiku 5.5 (xhigh)	41	49%	24%	52%	$0.61	25.9m	7.1M
Claude Code	Haiku 5.5 (max)	36	46%	30%	34%	$2.58	1.5h	13.8M
Claude Code	Haiku 5.5 (high)	35	46%	13%	46%	$0.36	18.4m	5.1M
Claude Code	Haiku 5.5 (medium)	34	47%	12%	42%	$0.23	14.0m	3.5M
Claude Code	Haiku 5.5 (low)	28	45%	6%	33%	$0.14	11.6m	2.4M
Codex	GPT-6.1 Sol (xhigh)	63	73%	55%	61%	$1.04	15.5m	3.2M
Codex	GPT-6 Astra (max)	62	68%	56%	62%	$7.47	29.4m	3.3M
Codex	GPT-6.1 Sol (medium)	61	72%	52%	61%	$0.70	10.9m	2.3M
Codex	GPT-6.1 Sol (high)	60	71%	50%	60%	$0.89	13.3m	2.8M
Codex	GPT-6.1 Sol (max)	60	70%	53%	58%	$1.55	24.4m	4M
Codex	GPT-6.1 Sol (low)	57	68%	49%	55%	$0.50	8.6m	1.7M
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

The Artificial Analysis Coding Agent Index is a composite score built from DeepSWE v1.1, Terminal-Bench 4.0, and SWE-Atlas-QnA.

It is useful for quick comparison, but it should be read alongside the per-eval breakdowns. Two agents with similar index values can still have different strengths across repository tasks, terminal workflows, and rubric-based evaluations.

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

Each point represents a coding-agent variant. Farther left means lower average cost per task, while higher on the chart means higher benchmark performance. The most efficient agents sit toward the upper-left: stronger results at lower cost.

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.

Non-cached input tokens sent to the model, including prompts, instructions, tool context, and task context that were not served from prompt cache.

Artificial Analysis Coding Agent Index vs. Total Tokens

Artificial Analysis Coding Agent Index vs. average total tokens per task

Color by

Most attractive quadrant

Each point represents a coding-agent variant. Farther left means lower average total token usage per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left achieve stronger results with fewer tokens.

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

This chart shows the average pay-per-token API cost per task across the Artificial Analysis Coding Agent Index, spanning DeepSWE v1.1, Terminal-Bench 4.0, and SWE-Atlas-QnA.

Where applicable, that cost model includes standard input pricing, discounted cached-input pricing, separate cache-write charges, and output pricing rather than treating all prompt tokens as if they were billed at the same uncached input rate.

It is intended to show pay-per-token API cost, not consumer plan pricing or the full operational cost of deploying the system in production. Infrastructure, engineering, and supervision costs are not the focus of this metric.

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

This chart uses agent wall time: how long the agent process was actively running on each task.

It does not include environment startup, verifier or judge time, or other harness overhead, so it is a cleaner comparison of how long the agent itself was working.

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

Each point represents a coding-agent variant. Farther left means shorter average agent runtime per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left deliver stronger results in less active agent time.

Claude Code vs. Codex

Coding Agent Index

Time per Task

Cost per Task

Comparison

Coding Agent Comparison

Model Variants

Model Variants

Performance

Artificial Analysis Coding Agent Index

What This Metric Means

Artificial Analysis Coding Agent Index vs. Cost per Task

How to Read This Chart

Token Usage

Token Usage per Task

Input Tokens

Artificial Analysis Coding Agent Index vs. Total Tokens

How to Read This Chart

Cost

Cost per Task

What Cost Is Measuring

Execution Time

Time per Task

What Execution Time Is Measuring

Artificial Analysis Coding Agent Index vs. Execution Time

How to Read This Chart