Model comparison

Model	Status	Perft test	Tech. quality	UX	Time	Tokens	Cost	Code size
Claude Opus 5.5 medium Anthropic Model profile →	loads	6/6	99	89	22 min 59 s	217,264	≈ $4.00 prices as of 06/10/2026	95 kB 1,987 lines
Claude Haiku 5.5 medium Anthropic Model profile →	loads	6/6	100	90	8 min 47 s	186,281	≈ $0.086 prices as of 06/10/2026	51 kB 1,197 lines
Claude Sonnet 5.5 medium Anthropic Model profile →	loads	6/6	98	83	11 min 03 s	153,928	≈ $1.42 prices as of 06/10/2026	62 kB 1,300 lines
GPT-6 Astra medium OpenAI Model profile →	loads	6/6	98	92	10 min 32 s	343,515	$2.26 prices as of 15/10/2026	38 kB 90 lines
GPT-6.1 Sol medium OpenAI Model profile →	loads	6/6	98	63	8 min 18 s	197,520	$0.29 prices as of 15/10/2026	47 kB 158 lines
GPT-6 Sol medium OpenAI Model profile →	loads	2/6	100	93	2 min 56 s	208,203	$0.28 prices as of 15/10/2026	36 kB 106 lines
GPT-6 Luna medium OpenAI Model profile →	loads	3/6	90	87	1 min 48 s	238,796	$0.015 prices as of 15/10/2026	30 kB 49 lines
GPT-5.6 Sol medium OpenAI Model profile →	loads	6/6	98	66	2 min 34 s	198,260	$0.31 prices as of 15/10/2026	22 kB 45 lines
GPT-5.6 Terra medium OpenAI Model profile →	loads	6/6	97	87	1 min 15 s	9,817	$0.11 prices as of 17/10/2026	22 kB 198 lines
GPT-5.6 Luna medium OpenAI Model profile →	broken fixed version →	–	79 after fix 79	74 after fix 82	48 s	7,303	$0.00837 prices as of 17/10/2026	17 kB 71 lines
GPT-5.5 medium OpenAI Model profile →	loads	6/6	98	69	2 min 11 s	13,572	$0.40 prices as of 17/10/2026	27 kB 310 lines
GPT-5.4 mini medium OpenAI Model profile →	loads	6/6	98	70	5 min 47 s	93,061	$0.42 prices as of 17/10/2026	65 kB 2,128 lines
Gemini 3.8 Flash medium Google Model profile →	loads	0/6	78	96	3 min 38 s	33,346	$0.12 prices as of 16/10/2026	78 kB 2,471 lines
DeepSeek V4 Pro high DeepSeek Model profile →	loads	6/6	98	93	7 min 31 s	66,806	$0.13 prices as of 16/10/2026	66 kB 1,532 lines
DeepSeek V4.1 Flash high DeepSeek Model profile →	loads	6/6	100	99	6 min 53 s	99,797	$0.060 prices as of 16/10/2026	84 kB 2,491 lines
Mistral Medium 3.5 high Mistral Model profile →	loads	0/6	89	87	4 min 36 s	42,592	$0.32 prices as of 17/10/2026	59 kB 2,106 lines
Mistral Small 4 high Mistral Model profile →	broken fixed version →	0/6	81 after fix 100	80 after fix 85	2 min 30 s	29,400	$0.017 prices as of 17/10/2026	57 kB 1,873 lines
Codestral 25.08 default Mistral Model profile →	loads	0/6	82	83	3 min 39 s	28,286	$0.025 prices as of 17/10/2026	107 kB 2,739 lines
GLM 5.3 high Z.ai Model profile →	broken	0/6	98	71	7 min 43 s	128,396	$0.56 prices as of 17/10/2026	72 kB 1,745 lines
Gemini 4 Argon medium Google Model profile →	loads	6/6	96	76	5 min 17 s	37,256	$0.37 prices as of 17/10/2026	95 kB 3,052 lines
Gemini 3.1 Pro medium Google Model profile →	loads	6/6	95	72	2 min 38 s	26,151	$0.31 prices as of 17/10/2026	58 kB 1,265 lines
Gemini 3.6 Flash medium Google Model profile →	broken fixed version →	–	80 after fix 98	80 after fix 94	2 min 47 s	29,952	$0.11 prices as of 17/10/2026	62 kB 1,866 lines
Gemini 3.5 Flash-Lite medium Google Model profile →	loads	0/6	100	70	1 min 23 s	21,623	$0.053 prices as of 17/10/2026	62 kB 1,847 lines
Gemini 3.1 Flash-Lite medium Google Model profile →	loads	0/6	95	79	7 s	2,681	$0.00351 prices as of 17/10/2026	5 kB 121 lines
Gemma 4 31B default Google Model profile →	broken fixed version →	–	79 after fix 96	80 after fix 67	5 min 57 s	13,057	$0.00 prices as of 17/10/2026	34 kB 832 lines
Mistral Large 4 none Mistral Model profile →	loads	0/6	100	89	42 min 27 s	127,511	$0.27 prices as of 17/10/2026	74 kB 1,972 lines

Cost = tokens priced with the API price list valid on the date shown next to the cost (prices change). ≈ = estimate (only the total token count is known), no ≈ = exact from input / output tokens. “Loads” = the page opens without errors; technical quality also checks behaviour during use – judge the quality in the viewer.