40 codex entries

Codex Violation Detection

Detects factual inconsistencies between a story bible and prose passages. The model must output structured XML identifying each violation with paragraph number and substring.

Tooling Reasoning

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
Claude Opus 4.6 (Reasoning)	100%
Gemini 3.1 Pro (Preview)	100%
Claude Sonnet 4.6 (Reasoning)	100%
Claude Opus 4.6	100%
Grok 4.20 (Beta, Reasoning)	100%
GPT-5.4 (Reasoning, Low)	100%
Grok 4.1 Fast	100%
Grok 4	100%
Grok 4 Fast	100%
Z.AI GLM 5 Turbo	100%
Qwen 3.5 35B	100%
Qwen 3.5 27B	100%
Gemini 2.5 Pro	99%
Claude Sonnet 4.5	99%
GPT-5 Mini	99%
GPT-5.4	99%
GPT-5.4 (Reasoning)	99%
MoonshotAI: Kimi K2.5	99%
GPT-5.4 Mini (Reasoning)	99%
Claude Opus 4.5	98%

	Score	Cost	Time
Stealth: Healer Alpha	98%	$0.0000	16.1s
Grok 4.1 Fast	100%	$0.0016	10.1s
Grok 4 Fast	100%	$0.0021	12.1s
Stealth: Hunter Alpha	97%	$0.0000	32.5s
Qwen 3.5 Flash	98%	$0.0036	47.1s
Z.AI GLM 5 Turbo	100%	$0.0057	13.3s
Gemini 2.5 Flash Lite (Reasoning)	97%	$0.0016	11.6s
Gemini 2.5 Flash	96%	$0.0027	3.3s
Z.AI GLM 4.7	98%	$0.0070	28.9s
Nemotron 3 Super	97%	$0.0000	2.8m
Inception Mercury 2	94%	$0.0029	4.4s
Gemini 2.5 Flash (Reasoning)	98%	$0.0072	10.7s
GPT-5 Mini	99%	$0.0075	1.3m
GPT-5.4	99%	$0.011	7.9s
Mistral Small 4 (Reasoning)	94%	$0.0020	15.1s
GPT-5.4 Mini (Reasoning, Low)	94%	$0.0054	6.2s
Qwen 3.5 9B	95%	$0.0020	2.0m
Stealth: Aurora Alpha	92%	—	5.8s
Mistral Large 3	94%	$0.0040	6.6s
ByteDance Seed 2.0 Mini	98%	$0.0030	2.6m

	Score	Cost	Speed	Stability
Grok 4.1 Fast	100%	$0.0016	10.1s	100%
Grok 4 Fast	100%	$0.0021	12.1s	100%
Z.AI GLM 5 Turbo	100%	$0.0057	13.3s	98%
Stealth: Healer Alpha	98%	$0.0000	16.1s	95%
GPT-5.4 (Reasoning, Low)	100%	$0.017	11.0s	100%
GPT-5.4	99%	$0.011	7.9s	96%
Gemini 2.5 Flash (Reasoning)	98%	$0.0072	10.7s	94%
Gemini 2.5 Flash Lite (Reasoning)	97%	$0.0016	11.6s	91%
GPT-5.4 Mini (Reasoning)	99%	$0.013	18.6s	97%
Grok 4.20 (Beta, Reasoning)	100%	$0.022	13.0s	100%
Gemini 2.5 Flash	96%	$0.0027	3.3s	90%
Stealth: Hunter Alpha	97%	$0.0000	32.5s	91%
Gemini 3 Flash (Preview, Reasoning)	98%	$0.0093	14.7s	92%
Qwen 3.5 35B	100%	$0.015	41.5s	98%
ByteDance Seed 2.0 Lite	97%	$0.0060	51.4s	97%
Z.AI GLM 4.7	98%	$0.0070	28.9s	92%
Inception Mercury 2	94%	$0.0029	4.4s	88%
Qwen 3.5 Flash	98%	$0.0036	47.1s	92%
Z.AI GLM 5	97%	$0.0082	33.0s	92%
GPT-5 Mini	99%	$0.0075	1.3m	96%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Total
71	Claude Opus 4.6 (Reasoning)	$0.077	25.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
50	Gemini 3.1 Pro (Preview)	$0.051	34.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
56	Claude Sonnet 4.6 (Reasoning)	$0.058	28.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
37	Claude Opus 4.6	$0.050	8.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
10	Grok 4.20 (Beta, Reasoning)	$0.022	13.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
5	GPT-5.4 (Reasoning, Low)	$0.017	11.0s	100%	100	100	100	100	100	100	100	100	100	100	100%
1	Grok 4.1 Fast	$0.0016	10.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
48	Grok 4	$0.045	50.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
2	Grok 4 Fast	$0.0021	12.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
3	Z.AI GLM 5 Turbo	$0.0057	13.3s	98%	100	100	100	100	100	100	100	100	100	97	100%
14	Qwen 3.5 35B	$0.015	41.5s	98%	100	100	100	100	100	100	100	100	100	97	100%
26	Qwen 3.5 27B	$0.015	1.1m	97%	100	100	100	100	100	100	100	100	100	95	100%
29	Gemini 2.5 Pro	$0.027	16.8s	95%	100	100	100	100	100	100	100	100	100	92	99%
30	Claude Sonnet 4.5	$0.030	7.3s	95%	100	100	100	100	100	100	100	100	100	92	99%
20	GPT-5 Mini	$0.0075	1.3m	96%	100	100	100	100	100	100	100	100	95	95	99%
6	GPT-5.4	$0.011	7.9s	96%	100	100	100	100	100	100	100	100	95	95	99%
45	GPT-5.4 (Reasoning)	$0.039	39.6s	96%	100	100	100	100	100	100	100	97	97	95	99%
24	MoonshotAI: Kimi K2.5	$0.012	54.2s	95%	100	100	100	100	100	100	100	100	95	92	99%
9	GPT-5.4 Mini (Reasoning)	$0.013	18.6s	97%	100	100	100	100	100	100	97	97	97	97	99%
52	Claude Opus 4.5	$0.050	8.2s	95%	100	100	100	100	100	97	97	97	97	97	98%
23	Aion 2.0	$0.0095	1.1m	95%	100	100	100	100	100	97	97	97	97	97	98%
4	Stealth: Healer Alpha	$0.0000	16.1s	95%	100	100	100	100	100	100	100	97	93	93	98%
44	ByteDance Seed 2.0 Mini	$0.0030	2.6m	95%	100	100	100	100	100	100	97	97	97	92	98%
39	o4 Mini High	$0.031	45.4s	94%	100	100	100	100	100	97	97	97	95	95	98%
7	Gemini 2.5 Flash (Reasoning)	$0.0072	10.7s	94%	100	100	100	100	100	100	97	95	95	92	98%
61	Qwen 3.5 397B A17B	$0.023	2.2m	93%	100	100	100	100	100	100	100	95	92	92	98%
22	o4 Mini	$0.016	25.1s	93%	100	100	100	100	100	97	97	97	97	92	98%
16	Z.AI GLM 4.7	$0.0070	28.9s	92%	100	100	100	100	100	100	100	97	92	88	98%
53	GPT-5.1	$0.034	49.6s	92%	100	100	100	100	97	97	97	97	95	93	98%
76	GPT-5	$0.056	1.4m	93%	100	100	100	100	100	100	97	95	92	92	98%
13	Gemini 3 Flash (Preview, Reasoning)	$0.0093	14.7s	92%	100	100	100	100	100	100	100	92	92	92	98%
58	Gemini 3 Pro (Preview)	$0.045	22.7s	92%	100	100	100	100	100	100	100	92	92	92	98%
18	Qwen 3.5 Flash	$0.0036	47.1s	92%	100	100	100	100	100	100	100	92	92	92	98%
19	Z.AI GLM 5	$0.0082	33.0s	92%	100	100	100	100	100	97	97	97	92	92	97%
47	Qwen 3.5 122B	$0.025	1.1m	93%	100	100	100	100	100	100	97	92	92	92	97%
51	Nemotron 3 Super	$0.0000	2.8m	93%	100	100	97	97	97	97	97	97	97	93	97%
28	ByteDance Seed 1.6	$0.0067	53.0s	91%	100	100	100	100	100	100	97	92	92	88	97%
8	Gemini 2.5 Flash Lite (Reasoning)	$0.0016	11.6s	91%	100	100	100	97	97	97	97	97	93	90	97%
15	ByteDance Seed 2.0 Lite	$0.0060	51.4s	97%	97	97	97	97	97	97	97	97	97	97	97%
12	Stealth: Hunter Alpha	$0.0000	32.5s	91%	100	100	100	100	100	97	93	92	92	92	97%
35	GPT-5.2	$0.023	22.0s	90%	100	100	100	95	95	95	95	95	95	91	96%
34	Claude Sonnet 4	$0.029	7.4s	94%	97	97	97	97	97	97	97	93	93	93	96%
11	Gemini 2.5 Flash	$0.0027	3.3s	90%	100	100	97	97	97	97	95	95	91	87	96%
25	Mistral Large 2	$0.016	6.3s	92%	100	97	97	97	97	97	93	93	93	92	96%
43	Claude Sonnet 4.6	$0.030	7.7s	90%	97	97	97	97	97	97	97	97	88	88	95%
42	Claude 3.7 Sonnet	$0.030	8.2s	90%	97	97	97	97	97	97	97	97	88	88	95%
62	Qwen 3.5 9B	$0.0020	2.0m	80%	100	100	100	100	97	97	97	97	92	70	95%
17	Inception Mercury 2	$0.0029	4.4s	88%	100	97	97	97	97	95	92	91	88	88	94%
31	Mistral Small 4 (Reasoning)	$0.0020	15.1s	83%	100	97	97	97	97	93	93	93	93	76	94%
21	Mistral Large 3	$0.0040	6.6s	87%	100	97	97	97	97	93	92	88	88	88	94%
27	GPT-5.4 Mini (Reasoning, Low)	$0.0054	6.2s	86%	97	97	97	97	97	97	97	92	83	83	94%
55	GPT-4o, May 13th (temp=0)	$0.038	3.4s	91%	93	93	93	93	93	93	93	93	90	90	93%
36	Mistral Large	$0.016	6.2s	86%	97	97	97	97	97	97	93	84	84	84	93%
32	MiniMax M2.7	$0.0021	24.4s	86%	100	97	93	93	93	93	92	90	88	84	92%
40	Stealth: Aurora Alpha	—	5.8s	83%	97	97	97	97	97	93	92	88	88	75	92%
103	Claude Opus 4	$0.144	11.2s	82%	100	100	97	92	92	92	92	88	84	83	92%
38	Qwen 3.5 Plus (2026-02-15)	$0.0041	20.6s	82%	100	100	92	92	92	92	92	87	83	83	91%
33	Gemini 3 Flash (Preview)	$0.0032	4.1s	83%	100	92	92	92	92	92	92	83	83	83	90%
69	Z.AI GLM 4.6	$0.0035	46.7s	69%	100	100	100	100	92	92	91	88	75	61	90%
41	MiniMax M2.5	$0.0021	26.0s	81%	97	97	93	93	93	90	90	84	80	79	90%
60	Z.AI GLM 4.7 Flash	$0.0017	1.0m	79%	97	97	93	92	92	90	90	84	80	76	89%
83	Claude 3.5 Sonnet	$0.056	9.4s	81%	97	93	88	88	88	88	88	84	84	84	88%
49	DeepSeek V3.2	$0.0019	17.7s	79%	95	93	93	92	92	88	84	80	79	79	88%
46	Gemini 3.1 Flash Lite (Preview)	$0.0024	1.9s	79%	97	91	88	88	88	88	88	84	83	75	87%
59	DeepSeek-V2 Chat	$0.0027	10.9s	73%	97	97	93	92	92	92	90	75	70	70	87%
75	GPT-5 Nano	$0.0044	1.6m	74%	97	95	93	87	84	84	84	84	83	75	87%
63	GPT-4o, Aug. 6th (temp=1)	$0.013	3.1s	76%	93	93	93	93	90	88	84	80	80	70	87%
54	ByteDance Seed 1.6 Flash	$0.0010	11.5s	76%	93	93	93	90	90	87	87	84	76	72	87%
91	Nemotron 3 Nano	$0.0030	4.2m	76%	97	93	90	88	88	87	87	84	76	75	86%
64	GPT-4o, Aug. 6th (temp=0)	$0.012	2.8s	76%	93	93	90	90	90	84	84	84	80	70	86%
57	Ministral 3 14B	$0.0014	6.2s	75%	93	92	90	88	88	87	83	83	72	71	85%
66	DeepSeek V3 (2024-12-26)	$0.0028	13.9s	72%	97	92	92	84	84	83	80	79	76	75	84%
84	GPT-4o, May 13th (temp=1)	$0.038	3.7s	74%	90	90	88	87	84	80	80	80	76	75	83%
68	Qwen3 235B A22B Instruct 2507	$0.0010	22.8s	73%	93	92	88	84	83	83	79	75	75	75	83%
70	DeepSeek V3 (2025-03-24)	$0.0020	9.9s	69%	93	92	88	87	83	79	75	75	74	71	82%
65	GPT-4.1 Mini	$0.0015	4.4s	73%	90	84	84	84	80	80	79	79	76	75	81%
77	DeepSeek V3.1	$0.0018	30.1s	65%	97	92	87	84	83	83	83	79	62	62	81%
79	GPT-4.1	$0.0092	9.9s	65%	100	88	83	83	79	79	79	79	75	62	81%
67	Gemma 3 27B	$0.0007	10.2s	74%	87	87	84	80	80	80	80	79	75	75	81%
74	Writer: Palmyra X5	$0.0072	17.3s	68%	90	88	88	84	79	79	79	76	75	67	81%
92	Claude Haiku 4.5	$0.010	5.0s	42%	97	97	92	88	88	88	88	83	79	3	80%
73	Grok 4.20 (Beta)	$0.0075	2.2s	67%	88	87	87	87	79	76	75	75	71	71	80%
80	Claude 3.5 Haiku	$0.0070	5.8s	64%	87	83	83	83	83	83	83	83	80	44	79%
72	Mistral Medium 3.1	$0.0038	7.9s	67%	92	91	83	83	83	76	75	75	68	67	79%
78	Hermes 3 405B	$0.0067	12.8s	69%	83	83	83	83	80	75	72	71	70	70	77%
85	Z.AI GLM 4.5	$0.0025	12.4s	58%	93	88	88	88	80	79	76	75	53	50	77%
87	GPT-5.4 Mini	$0.0037	1.9s	53%	95	95	95	91	87	80	66	52	52	52	76%
82	Inception Mercury	$0.0006	10.9s	61%	92	84	79	79	75	75	71	71	67	54	75%
81	Mistral Small Creative	$0.0008	3.6s	63%	84	83	83	79	79	79	75	67	61	52	74%
86	Ministral 3 3B	$0.0007	1.7s	59%	83	83	83	80	75	72	71	67	60	53	73%
97	Qwen 3 32B	$0.0014	23.3s	39%	97	90	87	80	79	79	71	61	55	3	70%
88	Qwen 2.5 72B	$0.0011	8.6s	59%	83	80	76	76	72	72	66	61	61	53	70%
95	Ministral 3 8B	$0.0011	3.5s	41%	84	84	84	83	83	79	67	67	63	0	69%
89	Mistral Small 4	$0.0008	3.4s	56%	79	79	76	75	72	72	66	60	56	44	68%
90	Mistral Small 3.2 24B	$0.0008	6.5s	55%	80	75	75	75	71	66	63	63	63	44	68%
98	Llama 3.1 Nemotron 70B	$0.0085	20.0s	48%	84	83	75	75	66	66	62	53	49	40	65%
94	Ministral 3B	$0.0003	1.3s	48%	83	80	72	66	60	60	60	55	55	55	65%
93	WizardLM 2 8x22b	$0.0051	8.0s	54%	76	75	75	66	66	66	62	55	53	51	64%
96	Hermes 3 70B	$0.0020	23.5s	50%	80	70	67	62	61	61	60	53	52	51	62%
101	Llama 3.1 70B	$0.0031	23.7s	35%	87	71	67	67	63	62	57	53	50	0	58%
99	Arcee AI: Trinity Mini	$0.0004	6.1s	42%	77	73	67	61	61	53	53	44	44	33	57%
117	Arcee AI: Trinity Large (Preview)	$0.0000	8.8m	35%	87	79	75	71	61	58	34	34	33	33	57%
107	GPT-5.4 Nano (Reasoning, Low)	$0.0011	4.9s	16%	93	92	92	88	88	61	41	0	0	0	55%
100	GPT-4o Mini (temp=0)	$0.0008	8.7s	42%	66	61	57	57	48	48	48	48	48	42	52%
106	Cohere Command R+ (Aug. 2024)	$0.020	10.4s	42%	66	66	60	60	60	48	44	41	40	33	52%
102	GPT-4o Mini (temp=1)	$0.0007	7.8s	41%	60	55	55	48	48	48	48	44	40	33	48%
114	GPT-5.4 Nano (Reasoning)	$0.0026	13.6s	4%	97	97	97	83	67	3	0	0	0	0	44%
104	Gemma 3 12B	$0.0003	7.1s	39%	55	48	48	48	48	40	40	40	40	33	44%
108	Gemini 2.5 Flash Lite	$0.0008	3.3s	28%	66	65	59	58	56	54	49	18	0	0	43%
105	Claude 3 Haiku	$0.0021	3.2s	40%	44	44	44	42	42	42	40	40	40	39	42%
111	GPT-5.4 Nano	$0.0008	3.2s	18%	83	80	66	54	54	48	3	0	0	0	39%
110	Mistral NeMO	$0.0011	6.2s	24%	72	48	41	38	37	36	35	33	33	0	37%
109	Gemma 3 4B	$0.0003	5.0s	33%	42	40	39	38	37	33	33	33	33	33	36%
115	Ministral 8B	$0.0007	2.2s	10%	75	75	71	67	67	0	0	0	0	0	35%
112	Llama 3.1 8B	$0.0002	36.7s	23%	60	57	44	42	38	33	32	25	3	3	34%
113	Rocinante 12B	$0.0015	5.4s	23%	44	42	38	33	33	33	33	17	3	0	28%
118	LFM2 24B	$0.0019	5.0m	25%	35	34	33	33	33	33	33	32	3	3	27%
116	GPT-4.1 Nano	$0.0003	2.2s	14%	33	18	17	17	17	17	17	17	0	0	15%
81.96%

Median	Evaluator	Top 3	Flop 3
76.8%	Accuracy (recall)	100GPT-5.4 (Reasoning, Low) 100Claude Sonnet 4.6 (Reasoning) 100Grok 4.1 Fast	0Rocinante 12B 0Claude 3 Haiku 0LFM2 24B
92.6%	Precision	100Claude Sonnet 4 100Z.AI GLM 5 Turbo 100Grok 4 Fast	1GPT-4.1 Nano 1LFM2 24B 7Rocinante 12B
100.0%	Structural validity	100Writer: Palmyra X5 100Mistral Small Creative 100Gemini 3 Flash (Preview)	45GPT-4.1 Nano 50Ministral 8B 51GPT-5.4 Nano (Reasoning)

Codex Violation Detection

40 codex entries

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)