Short text (~524 words), small codex (11 entries)

Codex Red Herring (False Positive Detection)

Tests whether models correctly report "no violations" when a codex is fully consistent with the prose passage. Models that hallucinate false violations (false positives) fail. Uses a 2×2 matrix of text length × codex size, with bare and detailed-entry variants.

Hallucination

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%
GPT-5 Mini	100%
Claude Opus 4.6	100%
ByteDance Seed 1.6	100%
Grok 4.1 Fast	100%
o4 Mini	100%
Gemini 2.5 Flash (Reasoning)	100%
Z.AI GLM 4.7 Flash	100%
ByteDance Seed 1.6 Flash	100%
Z.AI GLM 4.6	93%
GPT-5.1	93%
Z.AI GLM 5	93%
o4 Mini High	93%
Minimax M2.5	93%
Gemini 2.5 Flash Lite (Reasoning)	93%
Claude Sonnet 4.6 (Reasoning)	85%
GPT-5 Nano	85%
Arcee AI: Trinity Mini	81%
Z.AI GLM 4.5	78%

	Score	Cost	Time
Arcee AI: Trinity Mini	81%	$0.0012	36.6s
ByteDance Seed 1.6 Flash	100%	$0.0004	5.3s
Grok 4 Fast	77%	$0.0008	8.7s
Gemini 2.5 Flash Lite (Reasoning)	93%	$0.0012	8.6s
Grok 4.1 Fast	100%	$0.0007	7.5s
Llama 3.1 Nemotron 70B	67%	$0.0021	9.0s
Cohere Command R+ (Aug. 2024)	65%	$0.0046	2.5s
Minimax M2.5	93%	$0.0015	12.4s
ByteDance Seed 1.6	100%	$0.0017	16.9s
Gemini 2.5 Flash (Reasoning)	100%	$0.0051	8.5s
Z.AI GLM 4.5	78%	$0.0018	13.0s
GPT-5.2	76%	$0.0091	10.8s
Z.AI GLM 4.6	93%	$0.0029	18.0s
Z.AI GLM 4.7 Flash	100%	$0.0012	47.1s
GPT-5 Mini	100%	$0.0044	29.1s
o4 Mini	100%	$0.0097	18.9s
GPT-5.1	93%	$0.018	22.3s
Aion 2.0	78%	$0.0054	59.6s
GPT-5 Nano	85%	$0.0036	1.2m
Claude Opus 4.6	100%	$0.022	9.7s

	Score	Cost	Speed	Stability
ByteDance Seed 1.6 Flash	100%	$0.0004	5.3s	100%
Grok 4.1 Fast	100%	$0.0007	7.5s	100%
Gemini 2.5 Flash (Reasoning)	100%	$0.0051	8.5s	100%
ByteDance Seed 1.6	100%	$0.0017	16.9s	100%
GPT-5 Mini	100%	$0.0044	29.1s	100%
o4 Mini	100%	$0.0097	18.9s	100%
Z.AI GLM 4.7 Flash	100%	$0.0012	47.1s	100%
Claude Opus 4.6	100%	$0.022	9.7s	100%
Claude Opus 4.6 (Reasoning)	100%	$0.033	20.7s	100%
Gemini 3.1 Pro (Preview)	100%	$0.039	27.8s	100%
Gemini 2.5 Flash Lite (Reasoning)	93%	$0.0012	8.6s	55%
Minimax M2.5	93%	$0.0015	12.4s	55%
Z.AI GLM 4.6	93%	$0.0029	18.0s	56%
GPT-5.1	93%	$0.018	22.3s	55%
o4 Mini High	93%	$0.019	35.0s	55%
Z.AI GLM 5	93%	$0.013	1.4m	55%
Z.AI GLM 4.5	78%	$0.0018	13.0s	32%
Grok 4 Fast	77%	$0.0008	8.7s	29%
GPT-5 Nano	85%	$0.0036	1.2m	40%
GPT-5.2	76%	$0.0091	10.8s	27%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	# 6	# 7	# 8	# 9	# 10	Total
9	Claude Opus 4.6 (Reasoning)	$0.033	20.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
10	Gemini 3.1 Pro (Preview)	$0.039	27.8s	100%	100	100	100	100	100	100	100	100	100	100	100%
5	GPT-5 Mini	$0.0044	29.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
8	Claude Opus 4.6	$0.022	9.7s	100%	100	100	100	100	100	100	100	100	100	100	100%
4	ByteDance Seed 1.6	$0.0017	16.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
2	Grok 4.1 Fast	$0.0007	7.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
6	o4 Mini	$0.0097	18.9s	100%	100	100	100	100	100	100	100	100	100	100	100%
3	Gemini 2.5 Flash (Reasoning)	$0.0051	8.5s	100%	100	100	100	100	100	100	100	100	100	100	100%
7	Z.AI GLM 4.7 Flash	$0.0012	47.1s	100%	100	100	100	100	100	100	100	100	100	100	100%
1	ByteDance Seed 1.6 Flash	$0.0004	5.3s	100%	100	100	100	100	100	100	100	100	100	100	100%
13	Z.AI GLM 4.6	$0.0029	18.0s	56%	100	100	100	100	100	100	100	100	100	27	93%
14	GPT-5.1	$0.018	22.3s	55%	100	100	100	100	100	100	100	100	100	25	93%
16	Z.AI GLM 5	$0.013	1.4m	55%	100	100	100	100	100	100	100	100	100	25	93%
15	o4 Mini High	$0.019	35.0s	55%	100	100	100	100	100	100	100	100	100	25	93%
12	Minimax M2.5	$0.0015	12.4s	55%	100	100	100	100	100	100	100	100	100	25	93%
11	Gemini 2.5 Flash Lite (Reasoning)	$0.0012	8.6s	55%	100	100	100	100	100	100	100	100	100	25	93%
33	Claude Sonnet 4.6 (Reasoning)	$0.060	54.9s	40%	100	100	100	100	100	100	100	100	25	25	85%
19	GPT-5 Nano	$0.0036	1.2m	40%	100	100	100	100	100	100	100	100	25	25	85%
21	Arcee AI: Trinity Mini	$0.0012	36.6s	22%	100	100	100	100	100	100	100	100	6	0	81%
17	Z.AI GLM 4.5	$0.0018	13.0s	32%	100	100	100	100	100	100	100	29	25	25	78%
23	Aion 2.0	$0.0054	59.6s	31%	100	100	100	100	100	100	100	25	25	25	78%
81	Gemini 3 Pro (Preview)	$0.114	1.4m	31%	100	100	100	100	100	100	100	25	25	25	78%
18	Grok 4 Fast	$0.0008	8.7s	29%	100	100	100	100	100	100	100	25	25	17	77%
20	GPT-5.2	$0.0091	10.8s	27%	100	100	100	100	100	100	100	25	25	13	76%
25	Llama 3.1 Nemotron 70B	$0.0021	9.0s	18%	100	100	100	100	100	100	31	29	7	4	67%
26	Cohere Command R+ (Aug. 2024)	$0.0046	2.5s	14%	100	100	100	100	100	100	25	10	8	8	65%
75	Gemini 2.5 Pro	$0.072	54.5s	21%	100	100	100	100	100	50	25	25	25	25	65%
24	GPT-4.1 Nano	$0.0003	3.7s	18%	100	100	100	100	100	31	29	28	27	26	64%
84	Qwen 3.5 397B A17B	$0.022	4.2m	14%	100	100	100	100	100	25	25	25	25	17	62%
58	Gemini 3 Flash (Preview, Reasoning)	$0.030	54.0s	14%	100	100	100	100	100	25	25	25	25	17	62%
22	Claude Haiku 4.5	$0.0029	3.2s	30%	100	100	50	50	50	50	50	50	50	50	60%
35	Llama 3.1 70B	$0.0032	38.5s	11%	100	100	100	100	100	35	30	17	5	4	59%
80	Grok 4	$0.060	1.6m	11%	100	100	100	100	100	25	17	17	17	13	59%
27	Qwen 2.5 72B	$0.0003	5.9s	11%	100	100	100	100	42	33	32	29	25	17	58%
29	Claude Sonnet 4	$0.0056	2.1s	10%	100	100	100	100	50	25	25	25	25	17	57%
28	GPT-4.1 Mini	$0.0009	3.8s	9%	100	100	100	100	35	33	31	31	30	7	57%
38	Hermes 3 405B	$0.0016	2.9s	3%	100	100	100	100	17	17	17	17	13	8	49%
30	Hermes 3 70B	$0.0005	5.9s	11%	100	100	100	50	42	38	33	13	7	5	49%
79	Z.AI GLM 4.7	$0.014	2.0m	8%	100	100	100	25	25	25	25	25	25	25	48%
49	Claude 3.5 Sonnet	$0.014	5.7s	8%	100	100	100	42	38	25	17	13	13	10	46%
36	GPT-4.1	$0.0028	2.1s	12%	100	100	42	42	38	25	17	17	17	17	41%
82	GPT-5	$0.048	1.6m	10%	100	100	25	25	25	25	25	25	25	25	40%
46	Claude Sonnet 4.5	$0.0069	3.5s	10%	100	100	42	25	25	25	25	25	17	17	40%
56	Rocinante 12B	$0.0005	11.7s	2%	100	100	100	50	10	10	10	6	5	4	39%
40	DeepSeek-V2 Chat	$0.0006	2.5s	10%	100	100	25	25	25	25	25	25	25	17	39%
34	Claude Sonnet 4.6	$0.0099	6.2s	30%	42	38	38	38	38	35	35	35	35	8	34%
32	Ministral 3 14B	$0.0004	5.3s	24%	50	50	30	30	30	29	29	29	29	28	33%
31	Mistral Medium 3.1	$0.0011	2.8s	27%	42	42	42	35	32	31	30	30	25	17	32%
45	DeepSeek V3 (2024-12-26)	$0.0006	3.5s	14%	100	28	25	25	25	25	25	25	25	17	32%
51	GPT-4o, Aug. 6th (temp=1)	$0.0044	2.5s	13%	100	38	35	35	35	17	17	13	13	10	31%
77	Arcee AI: Trinity Large (Preview)	$0.0000	1.8m	13%	100	35	29	29	29	28	28	6	3	0	29%
37	Ministral 3B	$0.0001	3.5s	23%	50	30	30	29	28	28	28	28	27	8	29%
39	Ministral 3 3B	$0.0002	3.4s	24%	31	31	29	29	29	29	29	28	27	3	26%
41	Mistral Large 3	$0.0015	8.4s	25%	32	32	32	31	31	31	31	30	6	6	26%
55	DeepSeek V3.2	$0.0006	22.6s	21%	50	29	29	28	28	25	25	17	17	7	25%
61	GPT-4o Mini (temp=1)	$0.0003	3.7s	6%	100	33	32	31	13	13	10	8	7	7	25%
57	WizardLM 2 8x22b	$0.0011	26.8s	18%	50	50	33	25	25	25	17	13	8	6	25%
83	MoonshotAI: Kimi K2.5	$0.016	2.9m	25%	25	25	25	25	25	25	25	25	25	25	25%
50	Claude Opus 4.5	$0.0099	3.0s	25%	25	25	25	25	25	25	25	25	25	25	25%
43	Ministral 8B	$0.0003	7.2s	23%	28	28	28	27	27	27	27	27	26	2	25%
42	Mistral Small Creative	$0.0004	4.0s	24%	30	30	29	29	29	29	28	28	7	6	24%
52	Writer: Palmyra X5	$0.0025	12.5s	22%	29	28	25	25	25	25	25	17	17	13	23%
53	Mistral Large 2	$0.0059	7.8s	23%	35	33	31	31	31	30	10	10	8	7	23%
47	DeepSeek V3 (2025-03-24)	$0.0005	5.7s	23%	25	25	25	25	25	25	25	17	17	17	23%
44	Gemini 2.5 Flash	$0.0006	875ms	23%	25	25	25	25	25	25	25	17	17	17	23%
54	Mistral Large	$0.0059	7.7s	23%	33	32	32	31	31	30	10	10	8	6	22%
48	GPT-4o, Aug. 6th (temp=0)	$0.0032	1.3s	23%	25	25	25	25	25	25	25	17	17	13	22%
64	GPT-4o, May 13th (temp=1)	$0.010	1.9s	13%	42	35	31	17	17	17	17	13	13	8	21%
78	Qwen 3.5 Plus (2026-02-15)	$0.010	1.1m	13%	50	32	25	25	25	10	10	10	8	5	20%
62	Claude 3 Haiku	$0.0008	2.9s	8%	38	38	35	33	13	10	8	7	7	6	19%
74	Ministral 3 8B	$0.0022	1.4m	20%	28	28	28	27	27	27	26	2	0	0	19%
63	GPT-4o Mini (temp=0)	$0.0003	3.8s	8%	35	35	35	31	10	10	10	8	8	8	19%
76	Claude Opus 4	$0.034	5.8s	15%	25	25	25	17	17	17	17	17	13	13	18%
65	Claude 3.7 Sonnet	$0.0073	3.4s	12%	42	25	17	17	17	13	13	13	13	13	18%
59	DeepSeek V3.1	$0.0006	9.2s	17%	29	25	25	25	25	17	10	8	7	6	18%
60	Gemini 3 Flash (Preview)	$0.0012	1.6s	16%	25	17	17	17	17	17	17	17	13	13	17%
66	GPT-4o, May 13th (temp=0)	$0.0097	1.8s	14%	17	17	17	17	17	13	13	13	13	10	14%
72	Llama 3.1 8B	$0.0001	20.2s	4%	32	30	29	6	5	5	5	4	4	2	12%
67	Gemini 2.5 Flash Lite	$0.0003	1.1s	9%	17	17	13	10	10	10	6	6	4	3	9%
68	Gemma 3 27B	$0.0002	8.7s	8%	13	10	10	8	8	8	7	6	6	6	8%
70	Mistral Small 3.2 24B	$0.0003	2.6s	5%	10	10	7	6	6	6	5	4	4	4	6%
71	Gemma 3 4B	$0.0001	4.8s	5%	7	7	7	6	6	6	6	6	6	4	6%
69	Mistral NeMO	$0.0003	2.8s	6%	8	7	7	7	6	6	5	5	4	3	6%
73	Gemma 3 12B	$0.0002	10.5s	5%	7	6	6	5	5	5	5	5	4	3	5%
49.22%

Median	Evaluator	Top 3	Flop 3
42.5%	Correct "no violations" response	100Z.AI GLM 4.7 Flash 100Grok 4.1 Fast 100o4 Mini	0Gemma 3 4B 0Gemma 3 27B 0Gemini 3 Flash (Preview)
50.0%	No hallucinated violations	100Claude Opus 4.6 100Gemini 2.5 Flash (Reasoning) 100ByteDance Seed 1.6	3Ministral 3 8B 4Ministral 8B 8Ministral 3 3B

Codex Red Herring (False Positive Detection)

Short text (~524 words), small codex (11 entries)

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)