SurfMind Logosurfmind
ModelsSkillsBlogPricingWhat's new
chromeAdd to Chrome
SurfMind Logo
surfmind

AI assistant for every website you visit

Apps

  • Chrome extension
  • Firefox extension
  • Safari extension
  • Safari iOS extension

Resources

  • Account
  • Pricing
  • What's new
  • How to setup

Explore

  • Blog
  • Models
  • Leaderboard
  • Compare models

Company

  • Privacy Policy
  • Terms of Use
Β© 2026 SurfMind. All rights reserved.

Compare models

Put models side by side on price, context, capabilities, and benchmarks.

Browse modelsLeaderboard

Claude Haiku 4.5 is Anthropic's fast, affordable small model in the Claude 4 generation, balancing strong instruction-following and coding ability with low latency. It is designed for high-throughput agentic and chat applications where speed and cost efficiency are priorities.

Document analysis#31Mathematical#100Software & IT Services#101Writing, Literature, & Language#110
Learn more
AuthorAnthropic
CountryπŸ‡ΊπŸ‡Έ United States
ReleasedOct 15, 2025
Overview
Cost rate
1x
Context
200K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$1.00
Cached input$0.10
Output$5.00
Context
Context length200,000
Max output tokens64,000
Knowledge cutoff-
Performance
Throughput94 tok/s
Latency0.78s

Gemini 2.5 Flash is Google's fast, cost-efficient multimodal model built for high-volume everyday tasks like chat, summarization, and lightweight agentic workflows. This is the batch variant for asynchronous, lower-cost processing.

Image understanding#65Writing, Literature, & Language#105Legal & Government#114Entertainment, Sports, & Media#117
Learn more
AuthorGoogle
CountryπŸ‡ΊπŸ‡Έ United States
ReleasedJun 17, 2025
Overview
Cost rate
0.2x
Context
1M
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$0.15
Cached input$0.03
Output$1.25
Context
Context length1,048,576
Max output tokens65,535
Knowledge cutoff2025-01-31
Performance
Throughput-
Latency-

Benchmarks

Head-to-head scores across reasoning, coding, and agentic indices, plus per-domain rankings.

Intelligence

62.5
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
62.1
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
59.5
GLM-5.3 (max)
59.0
Grok 4.6 (medium)
29.9
Claude Haiku 4.5
20.3
Gemini 2.5 Flash (batch)

Coding

77.0
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
76.5
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
76.1
Gemini 3.7 Flash (high)
74.9

Automation & Tool Use

59.1
GLM-5.3 (max)
58.4
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
58.4
Qwen3.8 Max
57.1

Intelligence, coding & agentic scores from Artificial Analysis.

Domain

Multimodal

Software & IT Services

arena.ai
1541
Claude Opus 4.7 (high)
1540
Claude Opus 4.6 (high)
1539
Claude Fable 5
1529
Kimi K3 (max)
1526
muse-spark-1.2 (xHigh)
1526
Claude Opus 5 (high)
1523
Muse Spark 1.1
1522
Glm 5.3 (max)
1464
Claude Haiku 4.5
1422
Gemini 2.5 Flash (batch)

Popular comparisons

  • Ling-3.0-flash vs DeepSeek V4 Flash 0731
  • GLM 5.2 vs DeepSeek V4 Pro 0813
  • DeepSeek V3.2 vs GPT-5.6 Sol
  • GPT-5.6 Sol vs Claude Opus 4.8
  • Kimi K3 vs Claude Fable 5
  • Mistral Large vs Llama 4 Maverick
  • Llama 4 Maverick vs DeepSeek V3.2
  • Qwen3.8 Max vs Kimi K3
  • Claude Haiku 4.5 vs GPT-5.6 Luna
  • Claude Opus 4.8 vs Gemini 3.1 Pro Preview
  • Gemini 3.1 Pro Preview vs GPT-5.6 Sol
  • Grok 4.6 vs GPT-5.6 Sol
  • Claude Opus 5 vs Claude Opus 4.8
  • DeepSeek V3.2 vs Claude Opus 4.8
GPT-5.5 (xhigh)
74.8
GLM-5.3 (max)
43.9
Claude Haiku 4.5

Gemini 2.5 Flash (batch) has no data

Qwen3.8 2.4T A95B
56.6
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
16.5
Claude Haiku 4.5

Gemini 2.5 Flash (batch) has no data