Navigate
AI BENCHY
Advertise here

Muse Spark 1.2 (high) vs GPT-5.3-Codex (medium)

GPT-5.3-Codex (medium) leads on average score with 8.9 vs 8.8. GPT-5.3-Codex (medium) has the lower benchmark cost at $0.920 vs $1.632. GPT-5.3-Codex (medium) is faster at 16.96s vs 23.99s, with pass rates of 75.8% vs 83.3%.

Last updated at: 2026-08-05

Rank
#20
Total Output Tokens
349,571
Response Time (avg)
23.99s
Total Cost
$1.632
Rank
#18
Total Output Tokens
55,525
Response Time (avg)
16.96s
Total Cost
$0.920
Recommended model GPT-5.3-Codex (medium)

It has the best score here (8.9), while costing about 1.8x less than Muse Spark 1.2 (high).

Detailed comparison

Metric Muse Spark 1.2 Muse Spark 1.2 high Release: 2026-08-06 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05
Score 8.8 8.9
Rank #20 #18
Reliability 9.8 10.0
Consistency 8.7 8.6
Benchmark coverage 22/22 tests · 66/66 attempts 22/22 tests · 66/66 attempts
Tests Correct
Attempt pass rate 75.8% 83.3%
Flaky tests 4 4
Total Runs 66 66
Cost per result 10.880 5.748
Total Cost $1.632 $0.920
Input Price $1.250 / 1M $1.750 / 1M
Output Price $4.250 / 1M $14.000 / 1M
Total Input Tokens 117,028 81,268
Output Tokens 6,983 6,251
Reasoning Tokens 342,588 49,274
Response Time (avg) 23.99s 16.96s
Response Time (max) 192.00s 100.93s
Response Time (total) 527.70s 373.19s

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#20 Muse Spark 1.2

high
Cost
$0.057
Time
34.7s
Tokens
13,356 tok

#18 GPT-5.3-Codex

medium
Cost
$0.049
Time
54.9s
Tokens
3,580 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Muse Spark 1.2 10.0 10.0 100.0% 0 22.24s 7,275 351 47,857
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890

Quick Compare

Switch Comparison Pair