Ember-1 vs Qwen3.6 35B A3B

Compared models

Rank: #375
Total Output Tokens: 11,832
Response Time (avg): 22.65s
Total Cost: $0.786

Rank: #382
Total Output Tokens: 63,781
Response Time (avg): 8.43s
Total Cost: $0.105

Recommended model Qwen3.6 35B A3B

Its score stays close to the best score here (5.3 vs 5.4), while costing about 7.5x less than Ember-1.

Detailed comparison

Metric	Ember-1 Ember-1 none Release: 2026-09-28	Qwen3.6 35B A3B Qwen3.6 35B A3B none Release: 2026-04-20

Metric	Ember-1 Ember-1 none Release: 2026-09-28	Qwen3.6 35B A3B Qwen3.6 35B A3B none Release: 2026-04-20
Score	5.4	5.3
Rank	#375	#382
Reliability	8.8	10.0
Consistency	8.6	7.9
Attempts	69/69	69/69
Tests Correct
Attempt pass rate	43.5%	29.0%
Flaky tests	4	6
Total Runs	69	69
Cost per result	9.817	2.586
Total Cost	$0.786	$0.105
Input Price	$3.000 / 1M	$0.150 / 1M
Output Price	$15.000 / 1M	$1.000 / 1M
Cache Read Price	$0.300 / 1M	$0.050 / 1M
Cache Write Price	N/A	N/A
Total Input Tokens	202,617	272,479
Output Tokens	11,832	40,677
Reasoning Tokens	0	23,104
Response Time (avg)	22.65s	8.43s
Response Time (max)	93.12s	65.61s
Response Time (total)	520.91s	176.93s
Parameters	~2.8T total (~104B active)	35B total (3B 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.

#375 Ember-1

none

Cost: $0.156
Time: 224.6s
Tokens: 10,555 tok

#382 Qwen3.6 35B A3B

none

Cost: $0.008
Time: 30.1s
Tokens: 6,317 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

Category:

Agentic	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	6.1	3.1	66.7%	1		92.87s	175,191	9,168	0
Qwen3.6 35B A3B	5.2	3.2	33.3%	1		65.61s	178,489	17,876	0

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	5.2	7.9	41.7%	1		22.37s	796	867	0
Qwen3.6 35B A3B	3.6	7.6	16.7%	1		2.10s	696	1,571	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	5.5	10.0	33.3%	0		1.94s	7,485	393	0
Qwen3.6 35B A3B	5.5	10.0	33.3%	0		8.77s	7,911	960	10,201

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	3.0	10.0	0.0%	0		49.01s	12,162	327	0
Qwen3.6 35B A3B	3.8	5.8	33.3%	1		39.54s	74,650	19,202	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	6.4	5.9	66.7%	1		35.25s	4,017	161	0
Qwen3.6 35B A3B	10.0	10.0	100.0%	0		1.46s	7,788	248	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	5.3	10.0	33.3%	0		21.61s	804	68	0
Qwen3.6 35B A3B	2.9	7.2	11.1%	1		7.76s	792	36	10,293

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	5.0	10.0	0.0%	0		2.28s	540	160	0
Qwen3.6 35B A3B	4.4	3.0	33.3%	1		3.51s	520	124	1,421

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	6.4	5.8	66.7%	1		31.00s	509	81	0
Qwen3.6 35B A3B	6.2	5.8	66.7%	1		1.86s	709	75	1,189

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	10.0	10.0	100.0%	0		2.54s	840	569	0
Qwen3.6 35B A3B	3.2	9.9	0.0%	0		1.07s	714	573	0

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	3.0	10.0	0.0%	0		26.44s	0	0	0
Qwen3.6 35B A3B	3.0	10.0	0.0%	0		0ms	0	0	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Ember-1	3.0	10.0	0.0%	0		1.05s	273	38	0
Qwen3.6 35B A3B	3.0	10.0	0.0%	0		414ms	210	12	0

Switch Comparison Pair

Ember-1nonevsStep 3.5 Flashmedium Ember-1nonevsHy4 previewlow North Mini CodemediumFree AvailablevsEmber-1none Ember-1nonevsGranite 4.2 8Blow Qwen3.6 35B A3BnonevsInkling SmalllowFree Available Granite 4.2 8BlowvsQwen3.6 35B A3Bnone Nemotron 3.5 LightninghighFree AvailablevsQwen3.6 35B A3Bnone KAT Coder AIR V2.5highvsQwen3.6 35B A3Bnone Qwen3.6 35B A3BnonevsStep 3.5 Flashmedium Qwen3.6 35B A3BnonevsHy4 previewlow North Mini CodemediumFree AvailablevsQwen3.6 35B A3Bnone Mistral Small 4mediumvsQwen3.6 35B A3Bnone