AI judge results

Each judge sees two anonymous answers to the same native English writing prompt. It picks the stronger text or declares a tie, without seeing the model names.

A judge may also evaluate a pair containing a response from its own model; the answer identities remain hidden while it decides.

Three AI judges are active. Claude Opus 5.5 (since 23 September 2026) judges every pair; GPT-6 Sol (since 23 September) judges the pairs at the top and in the middle of the ranking; Muse Spark 1.3 (since 8 September) those in the middle and at the bottom. The judges therefore do not see the same pairs, so their tables are not directly comparable. The verdicts of former judges stay published: Claude Opus 5 (until 23 September 2026), GPT-5.6 Sol (until 20 September), Claude Fable 5.1 (paused on 19 September), and Claude Fable 5 and Claude Opus 4.8 (July 2026). Every verdict records the choice alone, with no score and no written rationale.

The tables add up every validated, published duel for each judge: wins, losses, ties and total comparisons. Blinding keeps each verdict focused on the writing rather than the brand behind it.

Ranks are ordered first by total wins, not by win rate or opponent strength; when coverage differs, read wins, losses and ties together with comparisons.

For the selected writing categories, ranks are assigned before publisher, size, model-status, generation-mode and access filters hide models, so gaps can remain in the visible numbering.

AI judges make it possible to compare many model pairs with a consistent protocol. They do not replace readers: human votes are counted separately in the human ranking, revealing where people and machines agree or disagree.

Latest included verdict: October 19, 2026 at 6:04 p.m. CEST

Latest modelsPrevious generationOlder models

Claude Fable 5

1,084 validated duel verdicts

Results from Claude Fable 5
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Fable 5 💡 adaptive high	758	68	79	905
2	MiniMax M3 💡 enabled	44	39	8	91
3	Claude Opus 5 💡 adaptive high	24	10	11	45
4	Qwen3.7 Plus 💡 enabled	15	53	4	72
6	Qwen3.7 Max 💡 enabled	14	49	8	71
7	MiMo V2.5 Pro 💡 enabled	14	53	5	72
8	DeepSeek V4 Pro 💡 enabled	13	51	7	71
9	Kimi K3 💡 enabled	9	16	20	45
10	Qwen3.6 27B Q8_0 💡 on* 🏠	9	28	3	40
11	DeepSeek V4 Flash 💡 enabled	9	58	5	72
12	GLM 5.2 💡 enabled	7	57	7	71
13	MiMo V2.5 💡 enabled	7	62	3	72
14	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	6	29	1	36
15	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	4	23	1	28
16	Qwen3.6 27B Q4_K_M 💡 on* 🏠	4	28	3	35
17	Gemma 4 12B Q8_0 ↯ 🏠	3	10	4	17
18	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	3	31	3	37
19	GPT-5.6 Luna 💡 high	3	39	3	45
20	GPT-5.6 Terra 💡 high	3	39	3	45
21	Qwen3.6 27B Q8_0 ↯ 🏠	2	12	4	18
22	Gemma 4 12B Q8_0 💡 on* 🏠	2	30	6	38
23	GPT-5.6 Sol 💡 high	2	36	6	44
24	Gemma 4 31B QAT-Q4_0 ↯ 🏠	1	4	1	6
25	Qwen3.6 35B A3B Q8_0 ↯ 🏠	1	11	5	17
26	Gemma 4 31B Q8_0 💡 on* 🏠	1	28	4	33
27	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	1	30	3	34
28	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	0	8	0	8
29	Gemma 4 26B A4B Q8_0 💡 on* 🏠	0	22	2	24
30	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	0	31	0	31

Claude Fable 5.1

1,741 validated duel verdicts

Results from Claude Fable 5.1
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Fable 5.1 💡 adaptive high	147	17	25	189
2	Claude Opus 5 💡 adaptive high	118	7	12	137
3	GLM 5.3 💡 max	102	34	31	167
4	Kimi K3 💡 enabled	96	22	19	137
5	Gemini 3.8 Flash 💡 high	79	64	35	178
6	Muse Spark 1.3 💡 high	76	79	33	188
7	Claude Sonnet 5 💡 adaptive high	69	51	22	142
8	Hy3 💡 high	59	72	32	163
9	GLM 5.3 Flash 💡 high	55	45	21	121
10	MiniMax M3 💡 enabled	51	66	18	135
11	GPT-6 Astra 💡 high	44	60	24	128
12	Grok 4.6 💡 high	40	10	5	55
13	GPT-5.6 Sol 💡 high	38	72	25	135
14	Seed 2.1 Turbo ↯	35	15	1	51
15	Aion 3.0 💡 mandatory	34	6	6	46
16	DeepSeek V4.1 Flash 💡 high	31	70	9	110
17	Inkling 💡 high	27	10	13	50
18	Qwen3.8 Max 💡 xhigh	25	17	13	55
19	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	20	3	8	31
20	Qwen3.8 27B Q6_K ↯ 🏠	18	8	7	33
21	Gemma 4 26B A4B Q6_K ↯ 🏠	16	5	7	28
22	Granite 4.2 30B Q6_K 💡 full 🏠	15	35	8	58
23	Gemma 4 31B Q6_K 💡 on* 🏠	14	9	4	27
24	Qwen3.8 27B Q4_K_M ↯ 🏠	13	7	5	25
26	Mistral Medium 3.5 💡 high	13	25	13	51
27	Gemma 4 E4B Q6_K ↯ 🏠	12	13	2	27
28	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	11	7	5	23
29	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	11	14	6	31
30	Gemma 4 31B Q6_K ↯ 🏠	11	16	2	29
31	DeepSeek V4 Flash 💡 enabled	10	2	5	17
32	Gemma 4 12B Q6_K 💡 on* 🏠	10	5	7	22
33	Qwen3.8 27B Q8_0 ↯ 🏠	10	9	5	24
34	Gemma 4 26B A4B Q6_K 💡 on* 🏠	9	11	8	28
35	Gemma 4 E4B Q4_K_M ↯ 🏠	9	16	4	29
36	Gemma 4 E4B Q6_K 💡 on* 🏠	9	17	3	29
37	Gemma 4 26B A4B Q8_0 ↯ 🏠	8	6	13	27
38	DeepSeek V4 Pro 💡 enabled	8	9	2	19
39	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	8	22	2	32
40	GLM 5.2 💡 enabled	7	9	4	20
41	Gemma 4 E4B Q4_K_M 💡 on* 🏠	7	18	2	27
42	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	7	21	2	30
43	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	6	12	4	22
44	MiMo V2.5 💡 enabled	6	13	1	20
45	MiMo V2.5 Pro 💡 enabled	5	6	9	20
46	Gemma 4 E4B Q8_0 ↯ 🏠	5	7	3	15
47	Gemma 4 31B Q8_0 ↯ 🏠	5	8	14	27
48	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	5	11	3	19
49	Gemma 4 12B Q8_0 ↯ 🏠	5	12	3	20
50	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	5	13	4	22
51	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	5	20	1	26
52	Gemma 4 12B QAT-Q4_0 ↯ 🏠	5	26	0	31
53	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	4	23	0	27
54	Gemma 4 E2B Q4_K_M ↯ 🏠	4	31	0	35
55	GPT-5.6 Terra 💡 high	3	13	5	21
56	Qwen3.6 35B A3B Q8_0 ↯ 🏠	2	19	0	21
57	Gemma 4 12B Q6_K ↯ 🏠	2	22	0	24
58	Hy4 Preview 💡 high	1	2	1	4
59	Qwen3.8 Flash 💡 high	1	2	1	4
60	Granite 4.2 8B Q8_0 💡 full 🏠	1	6	0	7
61	Gemma 4 31B QAT-Q4_0 ↯ 🏠	1	14	6	21
62	Qwen3.7 Plus 💡 enabled	1	18	1	20
63	GPT-5.6 Luna 💡 high	1	19	1	21
64	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	1	24	0	25
65	Gemma 4 E2B Q6_K ↯ 🏠	1	30	1	32
66	Gemma 4 31B Q8_0 💡 on* 🏠	0	1	2	3
67	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	0	2	1	3
68	Gemma 4 26B A4B Q8_0 💡 on* 🏠	0	2	1	3
69	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	0	2	1	3
70	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	0	2	1	3
71	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	0	2	1	3
72	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	0	2	1	3
73	Gemma 4 E2B Q8_0 💡 on* 🏠	0	3	1	4
74	Gemma 4 12B Q8_0 💡 on* 🏠	0	3	0	3
75	Granite 4.2 30B Q8_0 💡 full 🏠	0	4	3	7
76	Gemma 4 E2B Q4_K_M 💡 on* 🏠	0	4	0	4
77	Granite 4.2 30B Q4_K_M 💡 full 🏠	0	7	0	7
78	Granite 4.2 8B Q4_K_M 💡 full 🏠	0	7	0	7
79	Gemma 4 E4B Q8_0 💡 on* 🏠	0	13	0	13
80	Gemma 4 E2B Q6_K 💡 on* 🏠	0	23	0	23
81	Gemma 4 E2B Q8_0 ↯ 🏠	0	28	2	30

Claude Opus 4.8

843 validated duel verdicts

Results from Claude Opus 4.8
Rank	Model	Wins	Losses	Ties	Comparisons
1	Qwen3.6 27B Q4_K_M 💡 on* 🏠	83	53	10	146
2	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	78	68	5	151
3	MiniMax M3 💡 enabled	75	7	0	82
4	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	62	76	9	147
5	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	56	106	9	171
6	Gemma 4 31B Q8_0 💡 on* 🏠	38	93	7	138
7	GLM 5.2 💡 enabled	36	19	2	57
8	Qwen3.7 Max 💡 enabled	36	20	2	58
9	MiMo V2.5 Pro 💡 enabled	36	20	0	56
10	Qwen3.6 27B Q8_0 💡 on* 🏠	36	26	1	63
11	DeepSeek V4 Pro 💡 enabled	35	18	3	56
12	Claude Fable 5 💡 adaptive high	33	0	0	33
13	DeepSeek V4 Flash 💡 enabled	31	27	0	58
14	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	29	34	2	65
15	MiMo V2.5 💡 enabled	28	27	0	55
16	Qwen3.7 Plus 💡 enabled	27	26	4	57
17	Gemma 4 26B A4B Q8_0 💡 on* 🏠	27	48	3	78
18	Gemma 4 12B Q8_0 💡 on* 🏠	21	42	1	64
19	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	19	66	3	88
20	Qwen3.6 27B Q8_0 ↯ 🏠	6	7	0	13
21	GPT-5.6 Sol 💡 high	5	1	1	7
22	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	5	6	0	11
23	Gemma 4 12B Q8_0 ↯ 🏠	5	9	0	14
24	Qwen3.6 35B A3B Q8_0 ↯ 🏠	5	10	0	15
25	Gemma 4 31B QAT-Q4_0 ↯ 🏠	0	3	0	3

Claude Opus 5

33,671 validated duel verdicts

Results from Claude Opus 5
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Opus 5 💡 adaptive high	836	41	18	895
2	Kimi K3 💡 enabled	818	55	22	895
3	Claude Sonnet 5 💡 adaptive high	740	100	51	891
4	Claude Fable 5 💡 adaptive high	733	49	23	805
5	Claude Fable 5.1 💡 adaptive high	717	37	17	771
6	MiniMax M3 💡 enabled	711	151	31	893
7	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	677	193	62	932
8	GLM 5.3 💡 max	669	63	61	793
9	GPT-6 Astra 💡 high	669	80	72	821
10	GPT-5.6 Sol 💡 high	646	198	51	895
11	GLM 5.2 💡 enabled	646	211	37	894
12	GLM 5.3 Flash 💡 high	626	106	42	774
13	DeepSeek V4.1 Flash 💡 high	613	142	61	816
14	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	593	284	50	927
15	DeepSeek V4 Pro 💡 enabled	592	269	33	894
16	Hy3 💡 high	580	162	54	796
17	Aion 3.0 💡 mandatory	573	181	61	815
18	Muse Spark 1.3 💡 high	567	161	37	765
19	Gemini 3.8 Flash 💡 high	553	154	62	769
20	GPT-5.6 Terra 💡 high	545	291	59	895
21	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	541	457	58	1056
22	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	531	241	49	821
23	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	529	244	38	811
24	Qwen3.8 Max 💡 xhigh	525	204	78	807
25	Hy4 Preview 💡 high	522	209	61	792
26	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	508	253	60	821
27	Grok 4.6 💡 high	498	280	22	800
28	GPT-5.6 Luna 💡 high	492	352	50	894
29	Qwen3.8 Flash 💡 high	456	304	30	790
30	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	442	403	58	903
31	Gemma 4 31B Q8_0 💡 on* 🏠	425	417	68	910
32	Inkling 💡 high	403	344	59	806
33	Gemma 4 31B QAT-Q4_0 ↯ 🏠	402	453	68	923
34	Gemma 4 31B Q6_K 💡 on* 🏠	400	358	57	815
35	Gemma 4 26B A4B Q6_K 💡 on* 🏠	391	357	69	817
36	DeepSeek V4 Flash 💡 enabled	389	213	26	628
38	Gemma 4 31B Q8_0 ↯ 🏠	381	371	74	826
39	Gemma 4 26B A4B Q6_K ↯ 🏠	377	364	70	811
40	MiMo V2.5 Pro 💡 enabled	348	342	44	734
41	MiMo V2.5 💡 enabled	344	359	30	733
42	Gemma 4 31B Q6_K ↯ 🏠	337	412	71	820
43	MiMo V2.6 Pro fp8 💡 high	320	26	11	357
44	Qwen3.7 Plus 💡 enabled	300	400	43	743
45	Grok 4.7 💡 high	290	44	23	357
47	Qwen3.6 35B A3B Q8_0 ↯ 🏠	285	627	23	935
48	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	284	447	38	769
50	Qwen3.6 27B Q8_0 💡 on* 🏠	277	182	35	494
51	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	272	423	59	754
52	Gemma 4 26B A4B Q8_0 💡 on* 🏠	266	446	48	760
53	Qwen3.8 27B Q6_K ↯ 🏠	263	537	18	818
54	Gemma 4 12B Q8_0 💡 on* 🏠	258	453	52	763
55	Seed 2.1 Turbo ↯	248	330	17	595
56	Gemma 4 12B Q8_0 ↯ 🏠	248	446	49	743
57	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	245	461	65	771
58	Ling 3.0 Flash Q4_K_M ↯ 🏠	239	322	25	586
59	Qwen3.7 Max 💡 enabled	231	224	29	484
60	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	224	476	35	735
61	MiMo V2.6 Flash 💡 high	215	112	23	350
62	Qwen3.6 27B Q4_K_M 💡 on* 🏠	205	248	30	483
63	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	205	496	30	731
64	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	203	345	32	580
65	Gemma 4 12B Q6_K 💡 on* 🏠	198	336	44	578
66	Qwen3.8 27B Q4_K_M ↯ 🏠	183	610	27	820
67	Qwen3.8 27B Q8_0 ↯ 🏠	178	633	12	823
68	Ling 3.0 Flash Q4_K_M 💡 high 🏠	176	399	15	590
69	Gemma 4 26B A4B Q8_0 ↯ 🏠	166	374	36	576
70	Gemma 4 12B QAT-Q4_0 ↯ 🏠	163	382	26	571
71	Qwen3.6 27B Q8_0 ↯ 🏠	160	306	8	474
72	Muse Spark 1.2 💡 high	153	53	33	239
73	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	145	417	13	575
74	Gemma 4 12B Q6_K ↯ 🏠	136	404	28	568
75	Mistral Medium 3.5 💡 high	132	424	19	575
76	Gemma 4 E2B Q8_0 💡 on* 🏠	131	583	36	750
77	Gemini 3.7 Flash 💡 medium	130	53	57	240
78	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	125	601	10	736
79	Granite 4.2 30B Q6_K 💡 full 🏠	121	453	21	595
80	Granite 4.2 30B Q8_0 💡 full 🏠	108	416	24	548
81	Gemma 4 E4B Q8_0 💡 on* 🏠	108	626	9	743
82	Gemma 4 E4B Q8_0 ↯ 🏠	101	626	15	742
83	Gemma 4 E4B Q4_K_M ↯ 🏠	93	473	4	570
84	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	93	496	17	606
85	Agnes 3.0 Flash 💡 high	91	194	2	287
86	Granite 4.2 8B Q8_0 💡 full 🏠	83	470	14	567
87	Gemma 4 E4B Q6_K ↯ 🏠	83	474	7	564
88	Gemma 4 E4B Q6_K 💡 on* 🏠	76	493	6	575
89	Gemma 4 E2B Q8_0 ↯ 🏠	72	493	7	572
90	Granite 4.2 30B Q4_K_M 💡 full 🏠	71	459	20	550
91	Gemma 4 E2B Q4_K_M 💡 on* 🏠	65	663	22	750
92	Granite 4.2 8B Q4_K_M 💡 full 🏠	64	464	21	549
93	Gemma 4 E2B Q6_K 💡 on* 🏠	58	489	24	571
94	Gemma 4 E4B Q4_K_M 💡 on* 🏠	58	499	8	565
95	Gemma 4 E2B Q6_K ↯ 🏠	37	535	3	575
96	Gemma 4 E2B Q4_K_M ↯ 🏠	36	537	4	577

Claude Opus 5.5

23,191 validated duel verdicts

Results from Claude Opus 5.5
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Sonnet 5.5 💡 adaptive high	997	87	7	1091
2	GPT-6.1 Sol 💡 high	948	99	28	1075
3	Grok 4.7 💡 high	917	174	30	1121
4	GPT-6 Sol 💡 high	903	139	15	1057
5	Aion 3.5 💡 high	872	197	20	1089
6	MiMo V2.6 Pro fp8 💡 high	871	244	12	1127
7	GPT-6 Luna 💡 high	843	308	27	1178
8	Claude Opus 5.5 💡 adaptive high	690	6	2	698
9	MiMo V2.6 Flash 💡 high	621	476	15	1112
10	Agnes 3.0 Flash 💡 high	548	581	1	1130
11	Inkling 💡 high	340	222	8	570
12	Claude Fable 5.1 💡 adaptive high	327	36	2	365
13	Kimi K3 💡 enabled	310	41	7	358
14	GPT-6 Astra 💡 high	296	54	13	363
15	GLM 5.3 💡 max	295	63	5	363
16	GLM 5.3 Flash 💡 high	277	84	4	365
17	Gemma 4 26B A4B Q8_0 ↯ 🏠	273	265	22	560
18	Gemma 4 12B Q6_K 💡 on* 🏠	258	277	26	561
19	Gemini 3.8 Flash 💡 high	253	106	4	363
20	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	250	285	24	559
21	Gemma 4 12B Q6_K ↯ 🏠	249	301	20	570
22	MiniMax M3 💡 enabled	244	88	2	334
23	Qwen3.7 Plus 💡 enabled	240	221	11	472
24	Gemma 4 31B QAT-Q4_0 ↯ 🏠	240	226	12	478
25	DeepSeek V4.1 Flash 💡 high	232	124	9	365
26	Muse Spark 1.3 💡 high	232	140	10	382
27	Hy3 💡 high	231	142	6	379
28	GLM 5.2 💡 enabled	226	119	5	350
29	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	224	183	8	415
30	Hy4 Preview 💡 high	212	150	9	371
31	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	211	133	9	353
33	Gemma 4 26B A4B Q8_0 💡 on* 🏠	210	230	7	447
34	Ling 3.0 Flash Q4_K_M ↯ 🏠	210	293	4	507
35	Gemma 4 12B QAT-Q4_0 ↯ 🏠	210	335	20	565
36	Gemma 4 12B Q8_0 💡 on* 🏠	208	227	12	447
37	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	205	154	11	370
38	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	205	243	1	449
39	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	205	267	7	479
40	DeepSeek V4 Pro 💡 enabled	204	140	4	348
41	MiMo V2.5 Pro 💡 enabled	204	257	6	467
42	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	203	175	1	379
43	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	200	241	11	452
44	Qwen3.8 Max 💡 xhigh	199	163	11	373
45	MiMo V2.5 💡 enabled	199	262	7	468
46	GPT-5.6 Terra 💡 high	197	145	15	357
47	Seed 2.1 Turbo ↯	196	384	0	580
48	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	189	239	11	439
49	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	182	171	6	359
50	Gemma 4 31B Q6_K 💡 on* 🏠	181	167	9	357
51	Gemma 4 12B Q8_0 ↯ 🏠	175	281	12	468
52	Gemma 4 26B A4B Q6_K 💡 on* 🏠	167	186	6	359
53	Mistral Medium 3.5 💡 high	165	400	7	572
54	Ling 3.0 Flash Q4_K_M 💡 high 🏠	160	337	0	497
55	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	159	249	3	411
56	Granite 4.2 30B Q6_K 💡 full 🏠	154	424	4	582
57	Gemma 4 31B Q8_0 💡 on* 🏠	149	174	8	331
58	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	149	199	6	354
59	Qwen3.8 Flash 💡 high	149	215	9	373
60	Gemma 4 E4B Q6_K ↯ 🏠	146	380	3	529
61	Gemma 4 31B Q6_K ↯ 🏠	144	213	3	360
62	Gemma 4 26B A4B Q6_K ↯ 🏠	142	208	5	355
63	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	140	311	7	458
64	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	137	403	2	542
65	Granite 4.2 30B Q8_0 💡 full 🏠	134	352	7	493
66	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	133	344	6	483
67	Claude Sonnet 5 💡 adaptive high	127	16	0	143
68	Claude Opus 5 💡 adaptive high	126	3	0	129
69	Gemma 4 31B Q8_0 ↯ 🏠	123	231	12	366
70	Granite 4.2 8B Q4_K_M 💡 full 🏠	119	457	3	579
71	Ling 3.1 Flash 💡 high	118	17	3	138
72	Granite 4.2 8B Q8_0 💡 full 🏠	118	446	6	570
73	Qwen3.8 27B Q8_0 ↯ 🏠	116	248	0	364
74	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	113	432	3	548
75	Qwen3.6 35B A3B Q8_0 ↯ 🏠	112	328	2	442
76	GPT-5.6 Sol 💡 high	108	19	3	130
77	Gemma 4 E4B Q6_K 💡 on* 🏠	108	413	5	526
78	Claude Haiku 5.5 💡 adaptive high	105	28	6	139
79	Gemma 4 E4B Q4_K_M 💡 on* 🏠	105	414	5	524
80	Qwen3.8 27B Q6_K ↯ 🏠	102	260	1	363
81	Grok 4.6 💡 high	100	46	4	150
82	Gemma 4 E2B Q8_0 💡 on* 🏠	97	365	8	470
83	Qwen3.8 27B Q4_K_M ↯ 🏠	96	264	1	361
84	Gemma 4 E2B Q8_0 ↯ 🏠	96	461	15	572
85	Mistral Large 4 💡 high	94	44	7	145
86	Aion 3.0 💡 mandatory	94	57	3	154
87	Granite 4.2 30B Q4_K_M 💡 full 🏠	91	486	3	580
88	Gemma 4 E4B Q8_0 💡 on* 🏠	87	357	3	447
89	Gemma 4 E4B Q4_K_M ↯ 🏠	86	412	2	500
90	Gemma 4 E2B Q4_K_M ↯ 🏠	79	479	4	562
91	Gemma 4 E2B Q6_K 💡 on* 🏠	73	424	12	509
92	Nemotron 3 Ultra 💡 high	70	107	1	178
93	Gemma 4 E2B Q4_K_M 💡 on* 🏠	70	371	8	449
94	Gemma 4 E4B Q8_0 ↯ 🏠	68	369	6	443
95	Gemma 4 E2B Q6_K ↯ 🏠	65	455	4	524
96	GPT-5.6 Luna 💡 high	61	67	6	134
97	Nemotron 3.5 Lightning 💡 high	39	136	3	178
98	MiniMax M3.1 Flash 💡 high	1	2	0	3

GPT-5.6 Sol

26,222 validated duel verdicts

Results from GPT-5.6 Sol
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Fable 5 💡 adaptive high	1210	164	3	1377
2	GPT-5.6 Sol 💡 high	903	115	13	1031
3	Kimi K3 💡 enabled	576	82	4	662
4	GLM 5.2 💡 enabled	537	194	3	734
5	Claude Opus 5 💡 adaptive high	534	128	0	662
6	Claude Sonnet 5 💡 adaptive high	499	164	2	665
7	GPT-5.6 Terra 💡 high	497	159	6	662
8	MiniMax M3 💡 enabled	479	228	0	707
9	GPT-5.6 Luna 💡 high	476	179	7	662
10	GPT-6 Astra 💡 high	468	19	6	493
11	DeepSeek V4 Flash 💡 enabled	466	462	3	931
12	DeepSeek V4 Pro 💡 enabled	436	418	5	859
13	GLM 5.3 💡 max	429	68	11	508
14	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	427	209	6	642
15	Gemma 4 31B Q8_0 💡 on* 🏠	416	318	8	742
16	Claude Fable 5.1 💡 adaptive high	406	89	3	498
17	Qwen3.7 Plus 💡 enabled	397	287	9	693
18	Muse Spark 1.3 💡 high	395	96	4	495
19	DeepSeek V4.1 Flash 💡 high	386	99	3	488
20	Hy3 💡 high	384	125	2	511
21	Qwen3.8 Max 💡 xhigh	382	101	25	508
22	GLM 5.3 Flash 💡 high	378	175	1	554
23	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	364	391	4	759
24	Hy4 Preview 💡 high	362	172	6	540
25	Aion 3.0 💡 mandatory	359	152	1	512
26	Gemini 3.8 Flash 💡 high	353	139	6	498
27	Grok 4.6 💡 high	353	152	3	508
28	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	345	342	5	692
29	Gemma 4 31B QAT-Q4_0 ↯ 🏠	344	326	9	679
30	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	340	304	3	647
31	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	327	201	3	531
32	Qwen3.8 Flash 💡 high	324	213	7	544
33	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	324	359	7	690
34	Gemma 4 26B A4B Q8_0 💡 on* 🏠	316	395	3	714
35	MiMo V2.5 Pro 💡 enabled	315	372	7	694
36	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	311	426	3	740
38	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	307	439	4	750
39	Gemma 4 26B A4B Q6_K 💡 on* 🏠	299	209	3	511
40	Gemma 4 31B Q6_K 💡 on* 🏠	298	217	6	521
41	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	298	234	0	532
42	MiMo V2.5 💡 enabled	294	400	0	694
43	Gemma 4 12B Q8_0 💡 on* 🏠	289	396	0	685
44	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	281	223	5	509
45	Qwen3.7 Max 💡 enabled	279	181	5	465
46	Gemma 4 31B Q6_K ↯ 🏠	276	241	1	518
47	Muse Spark 1.2 💡 high	273	60	5	338
48	Gemma 4 12B Q8_0 ↯ 🏠	267	451	4	722
50	Qwen3.6 27B Q4_K_M 💡 on* 🏠	249	241	3	493
51	Gemini 3.7 Flash 💡 medium	247	83	9	339
52	Ling 3.0 Flash Q4_K_M ↯ 🏠	245	264	1	510
53	Gemma 4 26B A4B Q6_K ↯ 🏠	244	282	5	531
54	Gemma 4 31B Q8_0 ↯ 🏠	237	274	4	515
56	Granite 4.2 30B Q8_0 💡 full 🏠	232	286	2	520
57	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	225	397	4	626
58	Gemma 4 12B Q6_K 💡 on* 🏠	214	236	0	450
59	Qwen3.6 27B Q8_0 💡 on* 🏠	202	220	0	422
60	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	184	257	4	445
61	Inkling 💡 high	184	285	0	469
62	Ling 3.0 Flash Q4_K_M 💡 high 🏠	181	329	0	510
63	Gemma 4 E2B Q8_0 💡 on* 🏠	179	440	2	621
64	Gemma 4 12B QAT-Q4_0 ↯ 🏠	163	277	3	443
65	Qwen3.6 35B A3B Q8_0 ↯ 🏠	163	565	0	728
66	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	163	714	5	882
67	Mistral Medium 3.5 💡 high	157	269	2	428
68	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	152	288	2	442
69	Granite 4.2 8B Q8_0 💡 full 🏠	150	356	3	509
70	Gemma 4 12B Q6_K ↯ 🏠	142	287	1	430
71	Gemma 4 E2B Q4_K_M 💡 on* 🏠	142	475	2	619
72	Seed 2.1 Turbo ↯	140	294	0	434
73	Granite 4.2 30B Q6_K 💡 full 🏠	138	283	0	421
74	Granite 4.2 8B Q4_K_M 💡 full 🏠	134	388	1	523
75	Gemma 4 26B A4B Q8_0 ↯ 🏠	133	302	3	438
76	Qwen3.8 27B Q8_0 ↯ 🏠	127	387	0	514
77	Qwen3.8 27B Q6_K ↯ 🏠	126	389	0	515
78	Gemma 4 E4B Q8_0 💡 on* 🏠	119	489	1	609
79	Qwen3.8 27B Q4_K_M ↯ 🏠	115	396	0	511
80	Gemma 4 E4B Q8_0 ↯ 🏠	115	495	0	610
81	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	113	511	0	624
82	Gemma 4 E4B Q6_K 💡 on* 🏠	110	315	0	425
83	Qwen3.6 27B Q8_0 ↯ 🏠	108	358	0	466
84	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	104	325	0	429
85	Gemma 4 E2B Q6_K 💡 on* 🏠	104	347	0	451
86	Granite 4.2 30B Q4_K_M 💡 full 🏠	104	411	1	516
87	Gemma 4 E4B Q4_K_M ↯ 🏠	94	335	0	429
88	Gemma 4 E4B Q6_K ↯ 🏠	83	351	0	434
89	Gemma 4 E2B Q8_0 ↯ 🏠	78	343	0	421
90	Gemma 4 E4B Q4_K_M 💡 on* 🏠	78	352	0	430
91	Gemma 4 E2B Q4_K_M ↯ 🏠	69	352	0	421
92	Gemma 4 E2B Q6_K ↯ 🏠	50	373	0	423

GPT-6 Sol

14,468 validated duel verdicts

Results from GPT-6 Sol
Rank	Model	Wins	Losses	Ties	Comparisons
1	GPT-6.1 Sol 💡 high	1003	27	1	1031
2	Claude Opus 5.5 💡 adaptive high	944	103	0	1047
3	GPT-6 Luna 💡 high	859	180	0	1039
4	Claude Sonnet 5.5 💡 adaptive high	852	178	1	1031
5	Grok 4.7 💡 high	845	191	1	1037
6	Aion 3.5 💡 high	828	203	0	1031
7	MiMo V2.6 Pro fp8 💡 high	693	342	0	1035
8	MiMo V2.6 Flash 💡 high	468	529	0	997
9	GPT-6 Sol 💡 high	412	28	1	441
10	GPT-6 Astra 💡 high	260	19	1	280
11	Claude Haiku 5.5 💡 adaptive high	236	103	0	339
12	Ling 3.1 Flash 💡 high	223	120	0	343
13	Mistral Large 4 💡 high	222	117	0	339
14	Muse Spark 1.3 💡 high	211	66	1	278
15	DeepSeek V4.1 Flash 💡 high	202	79	0	281
16	Qwen3.8 Max 💡 xhigh	200	90	2	292
17	Hy4 Preview 💡 high	194	98	0	292
18	Hy3 💡 high	190	89	0	279
19	GLM 5.3 💡 max	189	91	0	280
20	Kimi K3 💡 enabled	183	83	0	266
21	GLM 5.2 💡 enabled	183	84	0	267
22	Gemini 3.8 Flash 💡 high	180	101	0	281
23	GLM 5.3 Flash 💡 high	168	109	0	277
24	Gemma 4 31B Q6_K 💡 on* 🏠	166	123	0	289
25	Claude Fable 5.1 💡 adaptive high	163	117	0	280
26	Gemma 4 31B Q8_0 💡 on* 🏠	158	106	0	264
27	GPT-5.6 Terra 💡 high	156	121	0	277
28	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	148	128	0	276
29	MiniMax M3 💡 enabled	147	114	0	261
30	Grok 4.6 💡 high	143	33	0	176
31	GPT-5.6 Sol 💡 high	139	7	0	146
32	Gemma 4 26B A4B Q6_K 💡 on* 🏠	132	158	0	290
33	Gemma 4 31B Q8_0 ↯ 🏠	132	159	0	291
34	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	129	137	0	266
35	Qwen3.8 Flash 💡 high	127	165	0	292
36	Aion 3.0 💡 mandatory	122	67	0	189
37	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	121	169	0	290
38	Gemma 4 31B Q6_K ↯ 🏠	119	172	0	291
39	Claude Opus 5 💡 adaptive high	118	32	0	150
40	Agnes 3.0 Flash 💡 high	116	613	0	729
41	Claude Sonnet 5 💡 adaptive high	114	48	0	162
42	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	114	174	0	288
43	Nemotron 3.5 Lightning 💡 high	109	113	0	222
44	Nemotron 3 Ultra 💡 high	109	121	0	230
45	GPT-5.6 Luna 💡 high	105	59	0	164
46	DeepSeek V4 Pro 💡 enabled	103	162	0	265
47	Gemma 4 26B A4B Q6_K ↯ 🏠	96	190	0	286
48	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	81	170	0	251
49	Qwen3.8 27B Q6_K ↯ 🏠	78	177	0	255
50	Qwen3.8 27B Q4_K_M ↯ 🏠	77	215	0	292
51	Qwen3.8 27B Q8_0 ↯ 🏠	73	218	0	291
52	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	71	123	0	194
53	Qwen3.7 Plus 💡 enabled	60	120	0	180
54	Inkling 💡 high	60	142	0	202
55	Gemma 4 31B QAT-Q4_0 ↯ 🏠	57	131	0	188
56	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	53	130	0	183
57	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	49	136	0	185
58	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	47	134	0	181
59	Gemma 4 12B Q8_0 💡 on* 🏠	44	141	0	185
60	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	39	150	0	189
61	Gemma 4 12B Q6_K 💡 on* 🏠	39	151	0	190
63	Gemma 4 26B A4B Q8_0 💡 on* 🏠	35	142	0	177
64	MiMo V2.5 Pro 💡 enabled	33	147	0	180
65	MiMo V2.5 💡 enabled	33	149	0	182
66	Gemma 4 12B Q6_K ↯ 🏠	32	160	0	192
67	Granite 4.2 30B Q8_0 💡 full 🏠	32	162	0	194
68	Gemma 4 12B Q8_0 ↯ 🏠	31	151	0	182
69	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	31	152	0	183
70	Mistral Medium 3.5 💡 high	31	162	0	193
71	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	30	160	0	190
72	Granite 4.2 8B Q8_0 💡 full 🏠	27	165	0	192
73	Gemma 4 12B QAT-Q4_0 ↯ 🏠	26	166	0	192
74	Seed 2.1 Turbo ↯	25	165	0	190
75	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	25	168	0	193
76	Ling 3.0 Flash Q4_K_M 💡 high 🏠	25	170	0	195
77	Gemma 4 26B A4B Q8_0 ↯ 🏠	23	167	0	190
78	Granite 4.2 8B Q4_K_M 💡 full 🏠	23	169	0	192
79	Granite 4.2 30B Q4_K_M 💡 full 🏠	22	170	0	192
80	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	21	164	0	185
81	Ling 3.0 Flash Q4_K_M ↯ 🏠	21	174	0	195
82	Qwen3.6 35B A3B Q8_0 ↯ 🏠	19	162	0	181
83	Gemma 4 E4B Q8_0 💡 on* 🏠	18	160	0	178
84	Gemma 4 E4B Q4_K_M 💡 on* 🏠	18	171	0	189
85	Granite 4.2 30B Q6_K 💡 full 🏠	17	174	0	191
86	MiniMax M3.1 Flash 💡 high	15	6	0	21
87	Gemma 4 E2B Q8_0 💡 on* 🏠	15	167	0	182
88	Gemma 4 E4B Q6_K 💡 on* 🏠	15	174	0	189
89	Gemma 4 E4B Q6_K ↯ 🏠	15	175	0	190
90	Gemma 4 E4B Q8_0 ↯ 🏠	14	176	0	190
91	Gemma 4 E2B Q4_K_M 💡 on* 🏠	13	175	0	188
92	Gemma 4 E2B Q6_K 💡 on* 🏠	13	177	0	190
93	Gemma 4 E2B Q8_0 ↯ 🏠	13	178	0	191
94	Gemma 4 E4B Q4_K_M ↯ 🏠	13	179	0	192
95	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	11	178	0	189
96	Gemma 4 E2B Q4_K_M ↯ 🏠	11	180	0	191
97	Gemma 4 E2B Q6_K ↯ 🏠	11	180	0	191
98	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	11	180	0	191

Muse Spark 1.3

14,571 validated duel verdicts

Results from Muse Spark 1.3
Rank	Model	Wins	Losses	Ties	Comparisons
1	Claude Opus 5.5 💡 adaptive high	472	8	6	486
2	GPT-6.1 Sol 💡 high	451	19	40	510
3	GPT-6 Sol 💡 high	397	66	24	487
4	Claude Sonnet 5.5 💡 adaptive high	375	111	14	500
5	Aion 3.5 💡 high	357	69	72	498
6	Grok 4.7 💡 high	348	37	19	404
7	GPT-6 Luna 💡 high	347	156	22	525
8	MiMo V2.6 Pro fp8 💡 high	330	58	16	404
9	GLM 5.3 Flash 💡 high	233	38	13	284
10	MiMo V2.6 Flash 💡 high	222	208	15	445
11	GPT-6 Astra 💡 high	213	10	34	257
12	Inkling 💡 high	211	77	14	302
13	Hy3 💡 high	210	57	23	290
14	Muse Spark 1.3 💡 high	210	68	21	299
15	Claude Fable 5.1 💡 adaptive high	209	47	7	263
16	Claude Sonnet 5 💡 adaptive high	202	21	8	231
17	Kimi K3 💡 enabled	202	36	13	251
18	GLM 5.3 💡 max	201	43	15	259
19	GLM 5.2 💡 enabled	200	67	23	290
20	Gemini 3.8 Flash 💡 high	199	71	29	299
21	MiniMax M3 💡 enabled	193	79	7	279
22	Claude Opus 5 💡 adaptive high	185	36	4	225
23	Hy4 Preview 💡 high	185	97	32	314
24	Grok 4.6 💡 high	182	59	18	259
25	Agnes 3.0 Flash 💡 high	180	304	4	488
26	GPT-5.6 Sol 💡 high	175	24	22	221
28	Qwen3.8 Max 💡 xhigh	172	98	31	301
29	Muse Glimmer 30B K-Quant 17GB 💡 high 🏠	171	102	23	296
30	Muse Glimmer 30B K-Quant Dynamic 💡 high 🏠	167	95	34	296
31	DeepSeek V4.1 Flash 💡 high	159	99	30	288
32	DeepSeek V4 Pro 💡 enabled	154	125	11	290
33	Granite 4.2 8B Q4_K_M 💡 full 🏠	152	168	16	336
34	Qwen3.8 27B Q8_0 💡 xhigh** 🏠	151	125	35	311
35	Gemma 4 31B QAT-Q4_0 💡 on* 🏠	150	111	36	297
36	Qwen3.8 Flash 💡 high	146	149	20	315
37	Qwen3.8 27B Q4_K_M 💡 xhigh** 🏠	143	126	33	302
38	Gemma 4 26B A4B Q6_K 💡 on* 🏠	141	139	29	309
39	Gemma 4 31B Q8_0 💡 on* 🏠	140	120	44	304
40	Qwen3.8 27B Q6_K ↯ 🏠	139	151	10	300
41	Gemma 4 12B Q8_0 💡 on* 🏠	138	132	34	304
42	Qwen3.8 27B Q6_K 💡 xhigh** 🏠	138	135	36	309
43	Gemma 4 31B Q6_K 💡 on* 🏠	134	136	43	313
44	Gemma 4 12B QAT-Q4_0 💡 on* 🏠	133	127	40	300
45	Aion 3.0 💡 mandatory	132	112	25	269
46	Seed 2.1 Turbo ↯	129	156	15	300
47	Qwen3.6 35B A3B Q8_0 💡 on* 🏠	127	121	38	286
48	Gemma 4 31B Q8_0 ↯ 🏠	125	135	39	299
49	Gemma 4 12B Q6_K 💡 on* 🏠	124	136	45	305
50	Gemma 4 31B QAT-Q4_0 ↯ 🏠	124	143	37	304
51	Qwen3.8 27B Q4_K_M ↯ 🏠	123	154	28	305
52	Gemma 4 31B Q6_K ↯ 🏠	122	156	24	302
53	GPT-5.6 Luna 💡 high	119	104	31	254
54	Granite 4.2 8B Q8_0 💡 full 🏠	119	181	20	320
55	Qwen3.7 Plus 💡 enabled	115	149	26	290
56	Gemma 4 26B A4B Q8_0 💡 on* 🏠	113	157	35	305
57	Qwen3.6 35B A3B Q4_K_M 💡 on* 🏠	111	165	19	295
58	Qwen3.6 35B A3B Q8_0 ↯ 🏠	110	172	17	299
59	GPT-5.6 Terra 💡 high	108	165	24	297
60	MiMo V2.5 Pro 💡 enabled	107	168	14	289
61	Gemma 4 12B Q8_0 ↯ 🏠	106	156	40	302
62	Gemma 4 26B A4B Q6_K ↯ 🏠	106	178	32	316
63	Gemma 4 26B A4B QAT-Q4_0 ↯ 🏠	104	176	20	300
64	MiMo V2.5 💡 enabled	98	164	28	290
65	Qwen3.8 27B Q8_0 ↯ 🏠	95	207	5	307
66	Gemma 4 26B A4B QAT-Q4_0 💡 on* 🏠	93	178	25	296
67	Gemma 4 12B QAT-Q4_0 ↯ 🏠	93	183	25	301
68	Qwen3.6 35B A3B Q4_K_M ↯ 🏠	93	204	8	305
69	Nemotron 3 Super 120B A12B Q4_K_M 💡 full 🏠	92	197	12	301
70	Gemma 4 12B Q6_K ↯ 🏠	90	199	17	306
71	Granite 4.2 30B Q8_0 💡 full 🏠	89	233	14	336
72	Ling 3.0 Flash Q4_K_M 💡 high 🏠	83	217	0	300
73	Nemotron 3 Nano Omni 30B A3B Q8_0 💡 on* 🏠	80	200	22	302
74	Gemma 4 26B A4B Q8_0 ↯ 🏠	79	203	18	300
75	Ling 3.0 Flash Q4_K_M ↯ 🏠	79	217	4	300
76	Gemma 4 E4B Q8_0 💡 on* 🏠	72	230	5	307
77	Nemotron 3 Nano Omni 30B A3B Q4_K_M 💡 on* 🏠	69	218	14	301
78	Granite 4.2 30B Q4_K_M 💡 full 🏠	68	258	8	334
79	DeepSeek V4 Flash 💡 enabled	65	27	12	104
80	Gemma 4 E4B Q6_K ↯ 🏠	63	235	7	305
81	Gemma 4 E4B Q4_K_M ↯ 🏠	59	232	13	304
82	Granite 4.2 30B Q6_K 💡 full 🏠	56	238	6	300
83	Gemma 4 E4B Q8_0 ↯ 🏠	54	234	19	307
84	Gemma 4 E2B Q8_0 💡 on* 🏠	54	237	20	311
85	Mistral Medium 3.5 128B Q4_K_M ↯ 🏠	53	229	18	300
86	Gemma 4 E4B Q6_K 💡 on* 🏠	52	227	26	305
87	Mistral Medium 3.5 💡 high	49	247	4	300
88	Gemma 4 E2B Q8_0 ↯ 🏠	41	258	6	305
89	Gemma 4 E2B Q6_K 💡 on* 🏠	39	252	16	307
90	Gemma 4 E2B Q4_K_M ↯ 🏠	39	263	2	304
91	Gemma 4 E2B Q4_K_M 💡 on* 🏠	34	265	11	310
92	Gemma 4 E4B Q4_K_M 💡 on* 🏠	26	269	13	308
93	Gemma 4 E2B Q6_K ↯ 🏠	23	283	1	307

The AIs have had their say. Your turn.

An AI judge can read thousands of duels without coffee or a lunch break. It still cannot tell us what makes you laugh, moves you, or keeps you reading. Your blind vote feeds a separate human ranking and helps reveal where human taste and machine judgment part ways.

Judge two anonymous texts

Claude Fable 5

Claude Fable 5.1

Claude Opus 4.8

Claude Opus 5

Claude Opus 5.5

GPT-5.6 Sol

GPT-6 Sol

Muse Spark 1.3

The AIs have had their say. Your turn.

Read next

Do AI judges favour their own model? Two of five do, by up to 19 points

The two main AI judges pick the same winner nine times out of ten. The disagreements are elsewhere

Which AI sounds least like AI? The best writers are the heaviest em-dash users

The human ranking