Navigate
Advertise here

Ember-1 (high) vs GPT-5.6 Sol

The average score is effectively tied at 7.1 vs 7.0. GPT-5.6 Sol has the lower benchmark cost at $0.201 vs $1.798. GPT-5.6 Sol is faster at 2.17s vs 56.77s, with pass rates of 71.2% vs 63.6%.

Last updated at: 2026-09-28

Compared models

Rank
#158
Total Output Tokens
110,125
Response Time (avg)
56.77s
Total Cost
$1.798
Rank
#160
Total Output Tokens
4,357
Response Time (avg)
2.17s
Total Cost
$0.201
Recommended model GPT-5.6 Sol

It has the best score here (7.0), while costing about 9.0x less than Ember-1 (high).

Detailed comparison

Metric Ember-1 Ember-1 high Release: 2026-09-28 GPT-5.6 Sol GPT-5.6 Sol none Release: 2026-07-09
Score 7.1 7.0
Rank #158 #160
Reliability 8.0 10.0
Consistency 7.3 9.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 71.2% 63.6%
Flaky tests 7 3
Total Runs 66 66
Cost per result 14.981 4.365
Total Cost $1.798 $0.201
Input Price $3.000 / 1M $2.000 / 1M
Output Price $15.000 / 1M $10.000 / 1M
Total Input Tokens 48,577 78,602
Output Tokens 7,345 4,357
Reasoning Tokens 102,780 0
Response Time (avg) 56.77s 2.17s
Response Time (max) 255.06s 12.81s
Response Time (total) 1248.88s 47.66s
Parameters ~2.8T total (~104B active) ~2T total (~150B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#158 Ember-1

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

#160 GPT-5.6 Sol

none
Cost
$0.116
Time
78.7s
Tokens
3,944 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
GPT-5.6 Sol 5.5 10.0 33.3% 0 1.39s 7,302 390 0

Quick Compare

Switch Comparison Pair