DOGPAY NEWS LEADERBOARD

AI model leaderboard

Evaluation sources How ranks are computed

Maths, logic and unfamiliar rules — can the model work out a problem it has not seen?

5 evaluations·2 operators·10/15 08:05 updated

Reasoning boardTOP 30

Ranked by the shared evidence of multiple public evaluations

Sort

The top 30 models, sortable by column
	Model
01	gpt-6.1-sol—Evidence-sensitive · 5 evaluationsOfficial —	5 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	99.0
02	GPT-6 AstraOpenAIEvidence-sensitive · 5 evaluationsOfficial $10 / $50DogRouter $5 / $25	5 evaluationsEvidence-sensitive	$1	$10	$50	$5 / $252026-09-30 verified	98.7
03	Claude Opus 5.5AnthropicEvidence-sensitive · 5 evaluationsOfficial $4 / $20DogRouter $2 / $10	5 evaluationsEvidence-sensitive	$0.2	$4	$20	$2 / $102026-09-30 verified	97.4
04	Claude Fable 5.1AnthropicEvidence-sensitive · 5 evaluationsOfficial $10 / $50DogRouter $5 / $25	5 evaluationsEvidence-sensitive	$0.25	$10	$50	$5 / $252026-09-30 verified	95.3
05	GPT-5.6 SolOpenAIEvidence-sensitive · 5 evaluationsOfficial $4 / $20DogRouter $2.8 / $14	5 evaluationsEvidence-sensitive	$0.4	$4	$20	$2.8 / $142026-09-30 verified	94.0
06	claude-sonnet-5.5anthropicEvidence-sensitive · 5 evaluationsOfficial —	5 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	92.7
07	GPT-6 SolOpenAIEvidence-sensitive · 5 evaluationsOfficial $2 / $10DogRouter $1 / $5	5 evaluationsEvidence-sensitive	$0.2	$2	$10	$1 / $52026-09-30 verified	91.4
08	Claude Opus 5AnthropicEvidence-sensitive · 5 evaluationsOfficial $5 / $25DogRouter $2.5 / $12.5	5 evaluationsEvidence-sensitive	$0.5	$5	$25	$2.5 / $12.52026-09-30 verified	90.9
09	Claude Fable 5AnthropicEvidence-sensitive · 5 evaluationsOfficial $10 / $50DogRouter $5 / $25	5 evaluationsEvidence-sensitive	$1	$10	$50	$5 / $252026-09-30 verified	90.3
10	GPT-5.6 TerraOpenAIEvidence-sensitive · 5 evaluationsOfficial $2 / $12DogRouter $1 / $6	5 evaluationsEvidence-sensitive	$0.2	$2	$12	$1 / $62026-09-30 verified	87.3
11	GPT-5.5OpenAIEvidence-sensitive · 5 evaluationsOfficial $5 / $30DogRouter $2.5 / $15	5 evaluationsEvidence-sensitive	$0.5	$5	$30	$2.5 / $152026-09-30 verified	86.6
12	Claude Opus 4.8AnthropicEvidence-sensitive · 5 evaluationsOfficial $5 / $25DogRouter $2.5 / $12.5	5 evaluationsEvidence-sensitive	$0.5	$5	$25	$2.5 / $12.52026-09-30 verified	81.8
13	Muse Spark 1.3MetaEvidence-sensitive · 5 evaluationsOfficial $1.25 / $4.25	5 evaluationsEvidence-sensitive	—	$1.25	$4.25	—	80.6
14	Gemini 3.7 FlashGoogleEvidence-sensitive · 5 evaluationsOfficial $0.75 / $3.75	5 evaluationsEvidence-sensitive	$0.075	$0.75	$3.75	—	78.7
15	Gemini 3.8 FlashGoogleEvidence-sensitive · 5 evaluationsOfficial $0.75 / $3.75	5 evaluationsEvidence-sensitive	$0.075	$0.75	$3.75	—	76.3
16	Qwen3.8 MaxAlibabaEvidence-sensitive · 5 evaluationsOfficial $1.79 / $5.38	5 evaluationsEvidence-sensitive	—	$1.79	$5.38	—	75.1
17	GPT-5.6 LunaOpenAIEvidence-sensitive · 5 evaluationsOfficial $0.2 / $1.2DogRouter $0.1 / $0.6	5 evaluationsEvidence-sensitive	$0.02	$0.2	$1.2	$0.1 / $0.62026-09-30 verified	74.3
18	claude-haiku-5-5—Evidence-sensitive · 5 evaluationsOfficial —	5 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	72.9
19	Grok 4.6xAIEvidence-sensitive · 5 evaluationsOfficial $2 / $6DogRouter $1.8 / $5.4	5 evaluationsEvidence-sensitive	$0.5	$2	$6	$1.8 / $5.42026-09-30 verified	72.0
20	Claude Sonnet 5AnthropicEvidence-sensitive · 5 evaluationsOfficial $2 / $10DogRouter $1 / $5	5 evaluationsEvidence-sensitive	$0.2	$2	$10	$1 / $52026-09-30 verified	70.5
21	DeepSeek V4 Pro 0813DeepSeekEvidence-sensitive · 5 evaluationsOfficial $1.34 / $4.03	5 evaluationsEvidence-sensitive	$0.045	$1.34	$4.03	—	68.2
22	Claude Opus 4.7AnthropicEvidence-sensitive · 5 evaluationsOfficial $5 / $25DogRouter $3.5 / $17.5	5 evaluationsEvidence-sensitive	$0.5	$5	$25	$3.5 / $17.52026-09-30 verified	66.7
23	DeepSeek V4.1 FlashDeepSeekEvidence-sensitive · 5 evaluationsOfficial $0.3 / $1.2DogRouter $0.3 / $1.2	5 evaluationsEvidence-sensitive	$0.006	$0.3	$1.2	$0.3 / $1.22026-09-30 verified	64.3
24	GPT-5.2 2025-12-11OpenAIEvidence-sensitive · 5 evaluationsOfficial $1.75 / $14	5 evaluationsEvidence-sensitive	$0.175	$1.75	$14	—	61.5
25	Grok 4.7xAIEvidence-sensitive · 5 evaluationsOfficial $2 / $6	5 evaluationsEvidence-sensitive	$0.5	$2	$6	—	61.0
26	Kimi K3Moonshot AIEvidence-sensitive · 5 evaluationsOfficial $2.99 / $14.94DogRouter $2.85 / $14.25	5 evaluationsEvidence-sensitive	$0.299	$2.99	$14.94	$2.85 / $14.252026-09-30 verified	60.6
27	Grok 4.5xAIEvidence-sensitive · 4 evaluationsOfficial $2 / $6DogRouter $1.9 / $5.7	4 evaluationsEvidence-sensitive	$0.3	$2	$6	$1.9 / $5.72026-09-30 verified	60.2
28	Claude Opus 4.6AnthropicEvidence-sensitive · 5 evaluationsOfficial $5 / $25	5 evaluationsEvidence-sensitive	$0.5	$5	$25	—	58.9
29	Gemini 3.1 Pro PreviewGoogleEvidence-sensitive · 5 evaluationsOfficial $2 / $12DogRouter $1.7 / $10.8	5 evaluationsEvidence-sensitive	$0.2	$2	$12	$1.7 / $10.82026-09-30 verified	57.3
30	GLM-5.3Z.aiEvidence-sensitive · 5 evaluationsOfficial $1.4 / $4.4DogRouter $1.4 / $4.4	5 evaluationsEvidence-sensitive	$0.26	$1.4	$4.4	$1.4 / $4.42026-09-30 verified	56.5

Each board shows at most 30 models

The consensus index is not an accuracy rate; ties keep the order the shared evidence establishes.

How to read this board

Aggregates several public evaluations; models differ in which ones they take part in.

See how it is computed →

About prices

API prices are shown in USD per million tokens by default. Vendor list prices and the DogRouter reference sit in separate columns; the latter is the relay price of a Dogpay sister service, carries a verification date and a link to its price page, is never shown as a discount, and does not affect the ranking. Cached price is the input rate on a cache hit; cache writes, storage and subscriptions are billed separately. CNY list prices are converted at the 2026-10-14 rate (欧洲央行).