PizeNews

Pize 是一款面向科学计算和统计分析的 AI 编程助手。它可在 Pize Code 和 Positron 中运行，也以 SDK 的形式提供。

Pize.ai

账户

行业快照

模型格局

一张图看清今天谁更强、这笔分数花多少钱。分数来自独立评测，不是 Pize 实测。

2026年10月17日当周Intelligence Index v4.3每日更新

Overall

谁在独立质量分上领先

0–100 · 条越长越强

Claude Opus 5.5 (Max, Default Fallback)

57.6

Claude Opus 5.5 (Xhigh, Default Fallback)

Claude Sonnet 5.5 (Max, Default Fallback)

Claude Opus 5.5 (High, Default Fallback)

53.6

Claude Fable 5.1 (Max, Default Fallback)

53.4

Claude Fable 5.1 (Xhigh, Default Fallback)

53.2

GPT-6 Astra (Max)

52.7

Gemini 4 Argon (High)

52.6

GPT-6 Astra (Xhigh)

52.4

Muse Wonder (Max)

52.4

Claude Sonnet 5.5 (Xhigh, Default Fallback)

51.9

GPT-6.1 Sol (Max)

51.8

Claude Opus 5.5 (Medium, Default Fallback)

51.2

Claude Fable 5.1 (High, Default Fallback)

51.2

GPT-6.1 Sol (Xhigh)

GPT-6 Astra (High)

50.9

Claude Opus 5 (Max)

50.8

GPT-6.1 Sol (High)

50.2

Claude Opus 5 (Xhigh)

49.7

GPT-6 Astra (Medium)

49.6

Overall

质量分 vs 成本

Claude Opus 5.5 (Max, Default Fallback)Claude Opus 5.5 (Xhigh, Default Fallback)Claude Sonnet 5.5 (Max, Default Fallback)Claude Opus 5.5 (High, Default Fallback)Claude Fable 5.1 (Max, Default Fallback)Claude Fable 5.1 (Xhigh, Default Fallback)GPT-6 Astra (Max)Gemini 4 Argon (High)GPT-6 Astra (Xhigh)Muse Wonder (Max)Claude Sonnet 5.5 (Xhigh, Default Fallback)GPT-6.1 Sol (Max)Claude Opus 5.5 (Medium, Default Fallback)Claude Fable 5.1 (High, Default Fallback)GPT-6.1 Sol (Xhigh)GPT-6 Astra (High)Claude Opus 5 (Max)GPT-6.1 Sol (High)Claude Opus 5 (Xhigh)GPT-6 Astra (Medium)

Coding

写代码 vs 成本

Science

科学推理 vs 成本

这份快照没有单独的科学指数，本图使用 Intelligence Index。

Overall

模型明细

按质量、成本或速度排序。可选择最多三个模型进行对比。

模型明细

Claude Opus 5.5 (Max, Default Fallback)Anthropic	57.6	57.6	57.6*	$5.98	97.46 tok/s	—	—
Claude Opus 5.5 (Xhigh, Default Fallback)Anthropic	56	56	56*	$3.46	86.55 tok/s	—	—
Claude Sonnet 5.5 (Max, Default Fallback)Anthropic	56	56	56*	$5.46	141.37 tok/s	—	—
Claude Opus 5.5 (High, Default Fallback)Anthropic	53.6	53.6	53.6*	$1.82	83.47 tok/s	—	—
Claude Fable 5.1 (Max, Default Fallback)Anthropic	53.4	81.6	53.4*	$7.63	70.94 tok/s	—	—
Claude Fable 5.1 (Xhigh, Default Fallback)Anthropic	53.2	80.7	53.2*	$5.98	64.06 tok/s	—	—
GPT-6 Astra (Max)OpenAI	52.7	76.9	52.7*	$3.26	57.43 tok/s	—	—
Gemini 4 Argon (High)Google	52.6	52.6	52.6*	$1.99	—	—	—
GPT-6 Astra (Xhigh)OpenAI	52.4	75.9	52.4*	$2.31	54.53 tok/s	—	—
Muse Wonder (Max)Meta	52.4	52.4	52.4*	$4.52	180.84 tok/s	—	—
Claude Sonnet 5.5 (Xhigh, Default Fallback)Anthropic	51.9	51.9	51.9*	$2.01	113.77 tok/s	—	—
GPT-6.1 Sol (Max)OpenAI	51.8	51.8	51.8*	$0.72	66.03 tok/s	—	—
Claude Opus 5.5 (Medium, Default Fallback)Anthropic	51.2	51.2	51.2*	$1.34	85.73 tok/s	—	—
Claude Fable 5.1 (High, Default Fallback)Anthropic	51.2	79.1	51.2*	$3.91	58.64 tok/s	—	—
GPT-6.1 Sol (Xhigh)OpenAI	51	51	51*	$0.39	58.49 tok/s	—	—
GPT-6 Astra (High)OpenAI	50.9	77.1	50.9*	$1.73	52.87 tok/s	—	—
Claude Opus 5 (Max)Anthropic	50.8	78	50.8*	$5.86	59.87 tok/s	—	—
GPT-6.1 Sol (High)OpenAI	50.2	50.2	50.2*	$0.32	57.54 tok/s	—	—
Claude Opus 5 (Xhigh)Anthropic	49.7	77	49.7*	$4.88	53.11 tok/s	—	—
GPT-6 Astra (Medium)OpenAI	49.6	76.7	49.6*	$1.54	48.5 tok/s	—	—

Overall

模型对比

3/3

Claude Opus 5.5 (Max, Default Fallback)

Anthropic

Overall: 57.6
Coding: 57.6
Science: 57.6
Cost per Index task: $5.98
速度: 97.46 tok/s

Claude Opus 5.5 (Xhigh, Default Fallback)

Anthropic

Overall: 56
Coding: 56
Science: 56
Cost per Index task: $3.46
速度: 86.55 tok/s

Claude Sonnet 5.5 (Max, Default Fallback)

Anthropic

Overall: 56
Coding: 56
Science: 56
Cost per Index task: $5.46
速度: 141.37 tok/s

Science

科学任务分项评分

按任务查看当前快照中可用的科学计算能力。

科学任务分项评分

0/160 来源直接提供

这份快照没有单独的科学指数，本图使用 Intelligence Index。

20/20聚合分数回退

模型	Python 数据分析	R 统计分析	生物信息学	数学推理	统计推断	文献理解	可复现实验代码	数据可视化
Claude Opus 5.5 (Max, Default Fallback)Anthropic	57.6*	57.6*	57.6*	57.6*	57.6*	57.6*	57.6*	57.6*
Claude Opus 5.5 (Xhigh, Default Fallback)Anthropic	56*	56*	56*	56*	56*	56*	56*	56*
Claude Sonnet 5.5 (Max, Default Fallback)Anthropic	56*	56*	56*	56*	56*	56*	56*	56*
Claude Opus 5.5 (High, Default Fallback)Anthropic	53.6*	53.6*	53.6*	53.6*	53.6*	53.6*	53.6*	53.6*
Claude Fable 5.1 (Max, Default Fallback)Anthropic	53.4*	53.4*	53.4*	53.4*	53.4*	53.4*	53.4*	53.4*
Claude Fable 5.1 (Xhigh, Default Fallback)Anthropic	53.2*	53.2*	53.2*	53.2*	53.2*	53.2*	53.2*	53.2*
GPT-6 Astra (Max)OpenAI	52.7*	52.7*	52.7*	52.7*	52.7*	52.7*	52.7*	52.7*
Gemini 4 Argon (High)Google	52.6*	52.6*	52.6*	52.6*	52.6*	52.6*	52.6*	52.6*
GPT-6 Astra (Xhigh)OpenAI	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*
Muse Wonder (Max)Meta	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*	52.4*
Claude Sonnet 5.5 (Xhigh, Default Fallback)Anthropic	51.9*	51.9*	51.9*	51.9*	51.9*	51.9*	51.9*	51.9*
GPT-6.1 Sol (Max)OpenAI	51.8*	51.8*	51.8*	51.8*	51.8*	51.8*	51.8*	51.8*
Claude Opus 5.5 (Medium, Default Fallback)Anthropic	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*
Claude Fable 5.1 (High, Default Fallback)Anthropic	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*	51.2*
GPT-6.1 Sol (Xhigh)OpenAI	51*	51*	51*	51*	51*	51*	51*	51*
GPT-6 Astra (High)OpenAI	50.9*	50.9*	50.9*	50.9*	50.9*	50.9*	50.9*	50.9*
Claude Opus 5 (Max)Anthropic	50.8*	50.8*	50.8*	50.8*	50.8*	50.8*	50.8*	50.8*
GPT-6.1 Sol (High)OpenAI	50.2*	50.2*	50.2*	50.2*	50.2*	50.2*	50.2*	50.2*
Claude Opus 5 (Xhigh)Anthropic	49.7*	49.7*	49.7*	49.7*	49.7*	49.7*	49.7*	49.7*
GPT-6 Astra (Medium)OpenAI	49.6*	49.6*	49.6*	49.6*	49.6*	49.6*	49.6*	49.6*