Navigate
Advertise here

Ember-1 (max) vs Qwen3.5-Flash

The average score is effectively tied at 5.9 vs 6.0. Qwen3.5-Flash has the lower benchmark cost at $0.073 vs $2.792. Qwen3.5-Flash is faster at 25.28s vs 98.92s, with pass rates of 57.6% vs 34.9%.

Last updated at: 2026-09-28

Compared models

Rank
#248
Total Output Tokens
180,806
Response Time (avg)
98.92s
Total Cost
$2.792
Rank
#243
Total Output Tokens
209,201
Response Time (avg)
25.28s
Total Cost
$0.073
Recommended model Qwen3.5-Flash

It has the best score here (6.0), while costing about 38.4x less than Ember-1 (max).

Detailed comparison

Metric Ember-1 Ember-1 max Release: 2026-09-28 Qwen3.5-Flash Qwen3.5-Flash none Release: 2026-02-24
Score 5.9 6.0
Rank #248 #243
Reliability 7.5 10.0
Consistency 7.7 9.3
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 57.6% 34.9%
Flaky tests 6 2
Total Runs 66 66
Cost per result 27.915 1.066
Total Cost $2.792 $0.073
Input Price $3.000 / 1M $0.065 / 1M
Output Price $15.000 / 1M $0.260 / 1M
Total Input Tokens 26,449 282,356
Output Tokens 4,183 209,201
Reasoning Tokens 176,623 0
Response Time (avg) 98.92s 25.28s
Response Time (max) 587.08s 480.96s
Response Time (total) 2176.20s 556.14s
Parameters ~2.8T total (~104B active) ~35B total (~3B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#248 Ember-1

max
Cost
$0.163
Time
229.4s
Tokens
11,002 tok

#243 Qwen3.5-Flash

none
Cost
$0.003
Time
47.4s
Tokens
7,799 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
Ember-1 5.2 4.4 55.6% 2 105.09s 3,362 1,149 27,957
Qwen3.5-Flash 5.5 10.0 33.3% 0 850ms 7,913 519 0

Quick Compare

Switch Comparison Pair