Navigate
Advertise here

ERNIE-Light-DT-1.0 (max) vs Muse Spark 1.3 (medium)

The average score is effectively tied at 9.0 vs 9.0. Muse Spark 1.3 (medium) has the lower benchmark cost at $1.712 vs $4.353. Muse Spark 1.3 (medium) is faster at 39.83s vs 103.37s, with pass rates of 81.2% vs 85.5%.

Last updated at: 2026-11-13

Compared models

Rank
#66
Total Output Tokens
1,003,960
Response Time (avg)
103.37s
Total Cost
$4.353
Rank
#65
Total Output Tokens
328,911
Response Time (avg)
39.83s
Total Cost
$1.712
Recommended model Muse Spark 1.3 (medium)

It has the best score here (9.0), while costing about 2.5x less than ERNIE-Light-DT-1.0 (max).

Detailed comparison

Metric ERNIE-Light-DT-1.0 ERNIE-Light-DT-1.0 max Release: 2026-11-12 Muse Spark 1.3 Muse Spark 1.3 medium Release: 2026-09-02
Score 9.0 9.0
Rank #66 #65
Reliability 8.9 10.0
Consistency 9.6 8.9
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 81.2% 85.5%
Flaky tests 1 3
Total Runs 69 69
Cost per result 24.179 9.507
Total Cost $4.353 $1.712
Input Price $1.130 / 1M $1.250 / 1M
Output Price $3.941 / 1M $4.250 / 1M
Cache Read Price $0.113 / 1M $0.150 / 1M
Cache Write Price N/A N/A
Total Input Tokens 350,977 250,676
Output Tokens 6,155 13,511
Reasoning Tokens 997,807 315,400
Response Time (avg) 103.37s 39.83s
Response Time (max) 473.48s 219.77s
Response Time (total) 2377.50s 916.20s
Parameters ~320B total (~18B active) ~1T total (~50B active)
Availability Closed Closed

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#66 ERNIE-Light-DT-1.0

max
OpenRouter returned no showcase content (finish_reason: length).
Cost
$0.259
Time
533.2s
Tokens
65,656 tok

#65 Muse Spark 1.3

medium
Cost
$0.025
Time
113.4s
Tokens
5,952 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
ERNIE-Light-DT-1.0 10.0 10.0 100.0% 0 97.26s 7,317 602 123,649
Muse Spark 1.3 10.0 10.0 100.0% 0 41.14s 7,275 1,182 46,737

Quick Compare

Switch Comparison Pair

ERNIE-Light-DT-1.0maxvsGemini 3.5 Flash LitehighGemini 4 CarbonlowvsMuse Spark 1.3mediumGemini 3.5 Flash LitehighvsMuse Spark 1.3mediumERNIE-Light-DT-1.0maxvsGemini 4 CarbonlowERNIE-Light-DT-1.0maxvsGemini 4 ArgonmediumClaude Opus 5lowvsERNIE-Light-DT-1.0maxClaude Opus 5lowvsMuse Spark 1.3mediumERNIE-Light-DT-1.0maxvsQwen3.8 Max (0902)mediumERNIE-Light-DT-1.0maxvsGemini 3.6 FlashlowGemini 3.6 FlashlowvsMuse Spark 1.3mediumMuse Spark 1.3mediumvsGLM 5.3 FlashmaxGemini 3.5 FlashlowvsMuse Spark 1.3medium