Navigate
Advertise here

Ember-1 (high) vs Qwen3.5-122B-A10B (medium)

Qwen3.5-122B-A10B (medium) leads on average score with 7.0 vs 6.9. Qwen3.5-122B-A10B (medium) has the lower benchmark cost at $1.152 vs $2.405. Ember-1 (high) is faster at 58.14s vs 66.96s, with pass rates of 71.0% vs 71.0%.

Last updated at: 2026-11-13

Compared models

Rank
#235
Total Output Tokens
121,223
Response Time (avg)
58.14s
Total Cost
$2.405
Rank
#229
Total Output Tokens
522,190
Response Time (avg)
66.96s
Total Cost
$1.152
Recommended model Qwen3.5-122B-A10B (medium)

It has the best score here (7.0), while costing about 2.1x less than Ember-1 (high).

Detailed comparison

Metric Ember-1 Ember-1 high Release: 2026-09-28 Qwen3.5-122B-A10B Qwen3.5-122B-A10B medium Release: 2026-02-24
Score 6.9 7.0
Rank #235 #229
Reliability 8.6 10.0
Consistency 7.2 8.3
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 71.0% 71.0%
Flaky tests 8 5
Total Runs 69 69
Cost per result 20.041 9.196
Total Cost $2.405 $1.152
Input Price $3.000 / 1M $0.260 / 1M
Output Price $15.000 / 1M $2.080 / 1M
Cache Read Price $0.300 / 1M N/A
Cache Write Price N/A N/A
Total Input Tokens 195,489 251,695
Output Tokens 12,475 49,415
Reasoning Tokens 108,748 472,775
Response Time (avg) 58.14s 66.96s
Response Time (max) 255.06s 519.30s
Response Time (total) 1337.19s 1539.99s
Parameters ~2.8T total (~104B active) 122B total (10B active)
Availability Closed Open source

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.

#235 Ember-1

high
Cost
$0.038
Time
55.1s
Tokens
2,671 tok

#229 Qwen3.5-122B-A10B

medium
Cost
$0.019
Time
48.7s
Tokens
6,034 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 8.2 7.2 88.9% 1 72.23s 7,144 1,281 23,093
Qwen3.5-122B-A10B 6.0 7.2 55.6% 1 114.48s 7,630 8,057 82,578

Switch Comparison Pair