Coding Agent Benchmarks

Codex vs. Muse Code

Comparison between Codex and Muse Code 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
Artificial Analysis Coding Agent Index v2.0 · Higher is better
Average agent wall time per task · Lower is better
Average API cost per task (USD) · Lower is better

Comparison

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

Metric
GPT-6 Astra (Max)
Muse Wonder Full (Max)
Analysis
Agent Harness
Codex
Muse Code
Representative Model
GPT-6 Astra (Max)
Muse Wonder Full (Max)
Coding Agent Index
55
59
Muse Code has a higher Coding Agent Index than Codex
FrontierCode v1.1
49
49
Both agents have the same FrontierCode v1.1 score
Terminal-Bench 4.0
56
59
Muse Code has a higher Terminal-Bench 4.0 score than Codex
SWE-Atlas-QnA-AA
59
69
Muse Code has a higher SWE-Atlas-QnA-AA score than Codex
Cost per Task
$7.04
-
Comparison not available
Time per Task
24.8m
34.9m
Codex has a lower time per task than Muse Code
Turns per Task
39.4
194.9
Codex has a lower turns per task than Muse Code
Token Usage per Task
3.23M
14.5M
Codex has a lower token usage per task than Muse Code
Cache Hit Rate
93%
96%
Muse Code has a higher cache hit rate than Codex

Model Variants

Evaluated model variants for Codex and Muse Code.

GPT-6 Astra (Max)
max
55
49
56
59
$7.04
24.8m
3.23M
GPT-6.1 Sol (Max)
max
54
49
53
60
$1.50
23.7m
3.94M
GPT-6.1 Terra (Xhigh)
xhigh
48
45
46
54
$0.69
16.4m
6.89M
GPT-6.1 Terra (Max)
max
48
42
48
54
$1.24
26.1m
12.3M
DeepSeek V4.1 Flash (Max)
max
47
53
28
61
$0.39
38.1m
27.2M
GPT-6.1 Terra (High)
high
46
43
42
53
$0.54
12.7m
5.6M
GPT-6.1 Terra (Medium)
medium
42
44
35
47
$0.39
10.2m
4.08M
GPT-6.1 Terra (Non-reasoning)
non-reasoning
39
46
25
46
$0.45
9.5m
5.78M
GPT-6.1 Terra (Low)
low
35
41
25
39
$0.20
6.3m
1.89M
GPT-6 Luna (Max)
max
31
40
16
38
$0.16
20.8m
8.69M
Muse Wonder Full (Max)
max
59
49
59
69
-
34.9m
14.5M
Muse Wonder (Max)
max
52
46
48
62
$8.05
24.5m
14.5M
Muse Ember (Max)
max
46
40
43
55
-
19.2m
18.8M
Muse Spark 1.3 (Max)
max
46
47
32
59
$3.91
23.3m
17.8M
Muse Ember (Xhigh)
xhigh
40
37
28
54
-
21.2m
17M
Muse Spark Open (Xhigh)
xhigh
26
23
6
51
$3.54
26.0m
13.3M

Performance

Performance across the Artificial Analysis Coding Agent Index.

Artificial Analysis Coding Agent Index

Artificial Analysis Coding Agent Index v2.0 incorporates 3 benchmarks: FrontierCode v1.1, Terminal-Bench 4.0, and SWE-Atlas-QnA-AA · 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

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