Compared models

Gemini 3.6 Flash (medium) vs GPT-5.6 Sol (low) vs GPT-5.6 Luna (high) vs GPT-5.6 Terra (high) benchmark comparisonGemini 3.6 Flash (medium) leads on Score with 9.9. Gemini 3.6 Flash (medium) leads on Reliability with 10.0. Gemini 3.6 Flash (medium) has the lowest Total Cost at $0.831. GPT-5.6 Sol (low) is fastest at 8.79s.

Recommended modelGemini 3.6 Flash (medium)It has the strongest score in this comparison (9.9) and the best overall balance of cost and response time across all 4 models.

Last updated at: 2026-07-21

Metric	Gemini 3.6 Flash Gemini 3.6 Flash medium Release: 2026-07-21	GPT-5.6 Sol GPT-5.6 Sol low Release: 2026-07-09	GPT-5.6 Luna GPT-5.6 Luna high Release: 2026-07-09	GPT-5.6 Terra GPT-5.6 Terra high Release: 2026-07-09

Metric	Gemini 3.6 Flash Gemini 3.6 Flash medium Release: 2026-07-21	GPT-5.6 Sol GPT-5.6 Sol low Release: 2026-07-09	GPT-5.6 Luna GPT-5.6 Luna high Release: 2026-07-09	GPT-5.6 Terra GPT-5.6 Terra high Release: 2026-07-09
Score	9.9	9.5	7.7	8.0
Rank	#1	#5	#48	#38
Reliability	10.0	10.0	10.0	10.0
Consistency	9.6	9.2	8.9	9.3
Tests Correct
Attempt pass rate	98.5%	86.4%	72.7%	68.2%
Flaky tests	1	2	3	2
Total Runs	66	66	66	66
Cost per result	3.955	5.391	6.780	7.533
Total Cost	$0.831	$0.971	$1.017	$1.055
Input Price	$1.500 / 1M	$5.000 / 1M	$1.000 / 1M	$2.500 / 1M
Output Price	$7.500 / 1M	$30.000 / 1M	$6.000 / 1M	$15.000 / 1M
Total Input Tokens	66,293	78,571	80,918	81,047
Output Tokens	2,000	4,476	5,088	5,055
Reasoning Tokens	95,464	14,770	150,910	51,736
Response Time (avg)	10.11s	8.79s	18.68s	11.32s
Response Time (max)	68.03s	53.91s	111.09s	91.49s
Response Time (total)	222.33s	193.33s	411.05s	249.14s

Hamster playing table tennis

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

#1 Gemini 3.6 Flash

medium

Cost: $0.079
Time: 47.9s
Tokens: 10,532 tok

#5 GPT-5.6 Sol

low

Cost: $0.062
Time: 26.7s
Tokens: 2,150 tok

#48 GPT-5.6 Luna

high

Cost: $0.033
Time: 34.2s
Tokens: 5,484 tok

#38 GPT-5.6 Terra

high

Cost: $0.055
Time: 30.2s
Tokens: 3,748 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:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	2.34s	516	149	4,489
GPT-5.6 Sol	8.3	10.0	75.0%	2.60s	606	174	492
GPT-5.6 Luna	8.3	10.0	75.0%	2.99s	606	162	1,265
GPT-5.6 Terra	8.3	10.0	75.0%	2.54s	606	158	700

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	0	17.49s	8,136	474	40,157
GPT-5.6 Sol	10.0	10.0	100.0%	0	11.25s	7,302	412	3,482
GPT-5.6 Luna	5.5	4.7	55.6%	2	15.63s	7,302	510	17,746
GPT-5.6 Terra	7.6	7.2	77.8%	1	9.14s	7,302	370	6,087

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	0	42.07s	41,732	405	11,531
GPT-5.6 Sol	10.0	10.0	100.0%	0	14.58s	55,372	2,896	1,539
GPT-5.6 Luna	10.0	10.0	100.0%	0	19.05s	57,719	3,366	8,005
GPT-5.6 Terra	8.7	6.9	83.3%	1	13.72s	57,848	3,461	3,174

Data parsing and extraction	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	4.26s	7,269	279	5,020
GPT-5.6 Sol	10.0	10.0	100.0%	1.82s	7,140	222	0
GPT-5.6 Luna	10.0	10.0	100.0%	2.18s	7,140	234	470
GPT-5.6 Terra	10.0	10.0	100.0%	938ms	7,140	222	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	8.2	7.2	88.9%	1	12.59s	651	12	20,611
GPT-5.6 Sol	5.3	7.2	44.4%	1	29.07s	723	71	7,822
GPT-5.6 Luna	7.7	10.0	66.7%	0	78.96s	723	69	96,395
GPT-5.6 Terra	5.3	10.0	33.3%	0	43.44s	723	70	32,942

General Intelligence	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	3.32s	492	116	1,539
GPT-5.6 Sol	10.0	10.0	100.0%	3.07s	477	99	135
GPT-5.6 Luna	5.0	10.0	0.0%	3.65s	477	117	563
GPT-5.6 Terra	5.1	10.0	0.0%	3.03s	477	113	216

Instructions following	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	9.9	10.0	100.0%	2.77s	627	71	3,067
GPT-5.6 Sol	10.0	10.0	100.0%	2.27s	660	90	146
GPT-5.6 Luna	9.9	10.0	100.0%	1.79s	660	97	481
GPT-5.6 Terra	10.0	10.0	100.0%	2.14s	660	96	319

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	0	2.53s	576	259	3,373
GPT-5.6 Sol	8.2	7.2	88.9%	1	3.44s	642	224	534
GPT-5.6 Luna	7.6	7.2	77.8%	1	14.55s	642	242	18,281
GPT-5.6 Terra	7.7	10.0	66.7%	0	5.45s	642	277	2,613

Tool Calling	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	8.55s	6,132	225	3,020
GPT-5.6 Sol	10.0	10.0	100.0%	7.56s	5,454	258	294
GPT-5.6 Luna	10.0	10.0	100.0%	4.98s	5,454	260	324
GPT-5.6 Terra	10.0	10.0	100.0%	4.97s	5,454	258	168

Trivia	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemini 3.6 Flash	10.0	10.0	100.0%	5.09s	162	10	2,657
GPT-5.6 Sol	10.0	10.0	100.0%	3.67s	195	30	326
GPT-5.6 Luna	3.0	10.0	0.0%	17.00s	195	31	7,380
GPT-5.6 Terra	3.0	10.0	0.0%	23.30s	195	30	5,517

Quick Compare

Switch Comparison Pair

Kimi K3maxvsGPT-5.6 Terrahigh Claude Opus 4.6mediumvsGPT-5.6 Lunahigh GPT-5.6 TerrahighvsInklingmedium Gemini 3.5 FlashhighvsGPT-5.6 Sollow GPT-5.6 LunahighvsGLM 5medium Claude Opus 4.8lowvsGPT-5.6 Lunahigh Gemini 3 Flash PreviewmediumvsGPT-5.6 Sollow Seed-2.0-LitemediumvsGPT-5.6 Terrahigh MiniMax M3mediumvsGPT-5.6 Lunahigh GPT-5.6 TerrahighvsQwen3.7 Plusmedium GPT-5.6 TerrahighvsStep 3.7 Flashmedium GPT-5.6 LunahighvsGrok Build 0.1medium