Claude 3.5 Haiku vs GPT-3.5 Turbo

Performance benchmarks + pricing comparison — updated April 2026

Claude 3.5 Haiku

Anthropic

Fast, cost-effective model for high-volume tasks. Great for code review and simple queries.

Input$0.800/M
Output$4.00/M
Context200K tokens
Best ForCode review, high-volume tasks, simple queries
Benchmark52/100

GPT-3.5 Turbo

OpenAI

Budget model for simple tasks. Being phased out but still widely used.

Input$0.500/M
Output$1.50/M
Context16K tokens
Best ForSimple chatbots, basic text generation
Benchmark40/100

Benchmark Performance Comparison

Third-party benchmark scores — higher is better. Data sourced from SWE-bench, LiveCodeBench, HumanEval, and BigCodeBench.

BenchmarkClaude 3.5 HaikuGPT-3.5 TurboLeader
Overall Score 52 40 Claude 3.5 Haiku leads by 12pts
SWE-bench Verified 45 32 Claude 3.5 Haiku leads by 13pts
LiveCodeBench 55 42 Claude 3.5 Haiku leads by 13pts
HumanEval 75 62 Claude 3.5 Haiku leads by 13pts
BigCodeBench 38 26 Claude 3.5 Haiku leads by 12pts

Cost Comparison by Scenario

Estimated cost per project with 30% cache hit rate. Actual costs may vary based on usage patterns.

ScenarioClaude 3.5 HaikuGPT-3.5 TurboSavings
Small Script (1K lines) $0.16 $0.06 GPT-3.5 Turbo saves $0.10 (62%)
Medium Feature (10K lines) $1.24 $0.48 GPT-3.5 Turbo saves $0.77 (62%)
Large Project (50K lines) $6.21 $2.38 GPT-3.5 Turbo saves $3.83 (62%)
Code Review (5K lines) $0.32 $0.13 GPT-3.5 Turbo saves $0.20 (61%)

Value Analysis (Price per Benchmark Score Point)

Lower is better — how much you pay for each point of benchmark performance.

ModelOverall ScorePrice per Score PointVerdict
Claude 3.5 Haiku 52 $0.015/pt Higher cost per point
GPT-3.5 Turbo 40 $0.013/pt Better value

GPT-3.5 Turbo delivers the best value at $0.013 per score point.

Strengths & Weaknesses

Claude 3.5 Haiku

  • + Fastest Claude model
  • + Cheapest option
  • + Good for code review
  • - Struggles with complex tasks
  • - Limited reasoning depth

GPT-3.5 Turbo

  • + Ultra-cheap
  • + Very fast
  • - Basic coding only

Verdict

GPT-3.5 Turbo is cheaper at $0.500/M, but Claude 3.5 Haiku scores higher on benchmarks (52 vs 40).

Choose GPT-3.5 Turbo for cost-sensitive projects, Claude 3.5 Haiku when performance matters most.

Compare with Other Models