Leaderboard · Nov 2025 – Nov 2026

Best AI models for coding, ranked by developers on Hacker News

The main table covers tools with at least 100 opinions. Less-discussed models are listed separately, because a high score from a few dozen people is a weaker signal.

Widely discussed models

#	Model	Approval	Last 90 days	Opinions
1	DeepSeek V4 Flash	83%	80%	151
2	Claude Opus 4.5	78%	90%	322
3	Claude Opus 5.5	75%	75%	186
4	GLM 5.2	75%	82%	142
5	DeepSeek V4 Pro	75%	67%	121
6	GPT-5.4	72%	–	114
7	GPT-5.5	69%	67%	236
8	GPT-5.6 Sol	67%	66%	247
9	Claude Opus 4.6	63%	63%	287
10	Claude Fable 5	57%	48%	188
11	Claude Opus 4.8	49%	57%	134
12	Claude Opus 4.7	42%	–	145
13	Claude Opus 5	33%	30%	162

Less-discussed models

Fewer than 100 opinions each. Promising, but treat the scores as early.

#	Model	Approval	Last 90 days	Opinions
14	GLM 5.3	85%	85%	67
15	Qwen 3 Coder	87%	–	39
16	Gemini 3 Flash	85%	–	31
17	DeepSeek V4.1 Flash	80%	80%	60
18	GLM 5.1	78%	–	67
19	Qwen 3.6	76%	71%	94
20	Qwen 3.6 27B	76%	56%	76
21	DeepSeek V4	78%	72%	48
22	Kimi K3	73%	74%	94
23	GLM 5	78%	–	30
24	GPT-5.3 Codex	74%	–	54
25	Kimi K2.5	74%	–	41
26	GPT-5.6	76%	75%	33
27	Qwen 3 Coder Next	72%	–	48
28	Qwen 3.8 27B	69%	69%	70
29	GLM 5.3 Flash	71%	71%	42
30	GPT-5.2	68%	–	82
31	Qwen 3.6 35B A3B	70%	56%	40
32	Kimi K2.6	70%	–	38
33	Claude Fable 5.1	69%	69%	35
34	Claude Sonnet 4.6	65%	–	65
35	Gemma 4	62%	–	68
36	Claude Sonnet 4.5	57%	–	97
37	Qwen 3.5	61%	–	41
38	Claude Sonnet 5	61%	41%	38
39	GPT-5	57%	–	62
40	Gemini 3	56%	–	70
41	GLM 4.7	56%	–	43
42	Gemini 3.1 Pro	54%	–	36
43	Gemini 3 Pro	52%	–	42
44	GPT-6 Astra	51%	51%	48
45	Qwen 3.8	50%	50%	53