DOGPAY NEWS LEADERBOARD

AI model leaderboard

Evaluation sources How ranks are computed

Real evaluations across many capabilities, to find the models that perform best overall.

19 evaluations·8 operators·10/04 08:05 updated

Overall boardTOP 30

Ranked by the shared evidence of multiple public evaluations

Sort

The top 30 models, sortable by column
	Model
01	Claude Opus 5.5AnthropicBuilding · 15 evaluationsOfficial $4 / $20DogRouter $2 / $10	15 evaluationsBuilding	$0.2	$4	$20	$2 / $102026-09-30 verified	87.2
02	Claude Fable 5.1AnthropicBuilding · 17 evaluationsOfficial $10 / $50DogRouter $5 / $25	17 evaluationsBuilding	$0.25	$10	$50	$5 / $252026-09-30 verified	85.6
03	GPT-6 AstraOpenAIEvidence-sensitive · 19 evaluationsOfficial $10 / $50DogRouter $5 / $25	19 evaluationsEvidence-sensitive	$1	$10	$50	$5 / $252026-09-30 verified	85.5
04	Claude Fable 5AnthropicEvidence-sensitive · 19 evaluationsOfficial $10 / $50DogRouter $5 / $25	19 evaluationsEvidence-sensitive	$1	$10	$50	$5 / $252026-09-30 verified	85.1
05	Gemini 3.7 FlashGoogleEvidence-sensitive · 17 evaluationsOfficial $0.75 / $3.75	17 evaluationsEvidence-sensitive	$0.075	$0.75	$3.75	—	81.2
06	gpt-6.1-sol—Evidence-sensitive · 15 evaluationsOfficial —	15 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	81.0
07	Claude Opus 5AnthropicEvidence-sensitive · 19 evaluationsOfficial $5 / $25DogRouter $2.5 / $12.5	19 evaluationsEvidence-sensitive	$0.5	$5	$25	$2.5 / $12.52026-09-30 verified	80.0
08	Muse Spark 1.3MetaEvidence-sensitive · 15 evaluationsOfficial $1.25 / $4.25	15 evaluationsEvidence-sensitive	—	$1.25	$4.25	—	77.1
09	Gemini 3.8 FlashGoogleEvidence-sensitive · 19 evaluationsOfficial $0.75 / $3.75	19 evaluationsEvidence-sensitive	$0.075	$0.75	$3.75	—	76.8
10	GPT-5.6 SolOpenAIEvidence-sensitive · 19 evaluationsOfficial $4 / $20DogRouter $2.8 / $14	19 evaluationsEvidence-sensitive	$0.4	$4	$20	$2.8 / $142026-09-30 verified	75.7
11	claude-sonnet-5.5anthropicEvidence-sensitive · 14 evaluationsOfficial —	14 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	73.7
12	GPT-5.5OpenAIEvidence-sensitive · 18 evaluationsOfficial $5 / $30DogRouter $2.5 / $15	18 evaluationsEvidence-sensitive	$0.5	$5	$30	$2.5 / $152026-09-30 verified	73.0
13	GPT-6 SolOpenAIEvidence-sensitive · 15 evaluationsOfficial $2 / $10DogRouter $1 / $5	15 evaluationsEvidence-sensitive	$0.2	$2	$10	$1 / $52026-09-30 verified	71.8
14	Kimi K3Moonshot AIEvidence-sensitive · 18 evaluationsOfficial $2.98 / $14.92DogRouter $2.85 / $14.25	18 evaluationsEvidence-sensitive	$0.298	$2.98	$14.92	$2.85 / $14.252026-09-30 verified	71.2
15	Qwen3.8 MaxAlibabaEvidence-sensitive · 17 evaluationsOfficial $1.79 / $5.37	17 evaluationsEvidence-sensitive	—	$1.79	$5.37	—	70.7
16	Claude Opus 4.7AnthropicEvidence-sensitive · 17 evaluationsOfficial $5 / $25DogRouter $3.5 / $17.5	17 evaluationsEvidence-sensitive	$0.5	$5	$25	$3.5 / $17.52026-09-30 verified	70.2
17	Muse Spark 1.2MetaEvidence-sensitive · 13 evaluationsOfficial $1.25 / $4.25	13 evaluationsEvidence-sensitive	—	$1.25	$4.25	—	68.9
18	Claude Opus 4.8AnthropicEvidence-sensitive · 19 evaluationsOfficial $5 / $25DogRouter $2.5 / $12.5	19 evaluationsEvidence-sensitive	$0.5	$5	$25	$2.5 / $12.52026-09-30 verified	67.4
19	Qwen3.8 Max 0902AlibabaEvidence-sensitive · 7 evaluationsOfficial $1.79 / $5.37	7 evaluationsEvidence-sensitive	—	$1.79	$5.37	—	66.9
20	GLM-5.3Z.aiEvidence-sensitive · 18 evaluationsOfficial $1.4 / $4.4DogRouter $1.4 / $4.4	18 evaluationsEvidence-sensitive	$0.26	$1.4	$4.4	$1.4 / $4.42026-09-30 verified	65.7
21	Claude Opus 4.6AnthropicEvidence-sensitive · 16 evaluationsOfficial $5 / $25	16 evaluationsEvidence-sensitive	$0.5	$5	$25	—	65.0
22	Muse Spark 1.1MetaEvidence-sensitive · 13 evaluationsOfficial $1.25 / $4.25	13 evaluationsEvidence-sensitive	—	$1.25	$4.25	—	61.1
23	Gemini 3 Pro PreviewGoogleEvidence-sensitive · 8 evaluationsOfficial —	8 evaluationsEvidence-sensitive	Unverified	Unverified	Unverified	—	60.5
24	Gemini 3.6 FlashGoogleEvidence-sensitive · 17 evaluationsOfficial $0.75 / $3.75	17 evaluationsEvidence-sensitive	$0.075	$0.75	$3.75	—	59.6
25	Gemini 3.5 FlashGoogleEvidence-sensitive · 17 evaluationsOfficial $1.5 / $9	17 evaluationsEvidence-sensitive	$0.15	$1.5	$9	—	58.3
26	Grok 4.6xAIEvidence-sensitive · 17 evaluationsOfficial $2 / $6DogRouter $1.8 / $5.4	17 evaluationsEvidence-sensitive	$0.5	$2	$6	$1.8 / $5.42026-09-30 verified	57.6
27	GPT-5.4OpenAIEvidence-sensitive · 11 evaluationsOfficial $2.5 / $15	11 evaluationsEvidence-sensitive	$0.25	$2.5	$15	—	57.4
28	DeepSeek V4.1 FlashDeepSeekEvidence-sensitive · 11 evaluationsOfficial $0.3 / $1.2DogRouter $0.3 / $1.2	11 evaluationsEvidence-sensitive	$0.006	$0.3	$1.2	$0.3 / $1.22026-09-30 verified	54.6
29	GPT-5.6 TerraOpenAIEvidence-sensitive · 19 evaluationsOfficial $2 / $12DogRouter $1 / $6	19 evaluationsEvidence-sensitive	$0.2	$2	$12	$1 / $62026-09-30 verified	54.2
30	DeepSeek V4 Pro 0813DeepSeekEvidence-sensitive · 15 evaluationsOfficial $1.34 / $4.03	15 evaluationsEvidence-sensitive	$0.045	$1.34	$4.03	—	52.5

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 2026-10-02 rate (欧洲央行).