Claude 3.5 Haiku vs GPT-5.1 Codex
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
GPT-5.1 Codex by OpenAI wins on 10 of 14 benchmarks against Claude 3.5 Haiku by Anthropic, which leads on 4. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.
Category-by-Category Breakdown
General Intelligence: In general intelligence, GPT-5.1 Codex scores 1395 on Chatbot Arena ELO compared to Claude 3.5 Haiku's 1180, while GPT-5.1 Codex scores 82.0% on MMLU-Pro compared to Claude 3.5 Haiku's 60.0%.
Coding: In coding, GPT-5.1 Codex scores 96.0% on HumanEval+ compared to Claude 3.5 Haiku's 74.0%, while GPT-5.1 Codex scores 78.0% on SWE-bench Verified compared to Claude 3.5 Haiku's 22.0%, while GPT-5.1 Codex scores 85.0% on LiveCodeBench compared to Claude 3.5 Haiku's 28.0%.
Math: In math, GPT-5.1 Codex scores 85.0% on MATH compared to Claude 3.5 Haiku's 62.0%, while GPT-5.1 Codex scores 95.0% on GSM8K compared to Claude 3.5 Haiku's 84.0%.
Reasoning: In reasoning, GPT-5.1 Codex scores 65.0% on GPQA Diamond compared to Claude 3.5 Haiku's 35.0%, while GPT-5.1 Codex scores 52.0% on ARC-AGI compared to Claude 3.5 Haiku's 12.0%.
Context: In context, GPT-5.1 Codex scores 400K on Context Length compared to Claude 3.5 Haiku's 200K.
Pricing Comparison
Claude 3.5 Haiku costs $0.80/1M input tokens and $4.0/1M output tokens, while GPT-5.1 Codex costs $1.3/1M input and $10.0/1M output. Claude 3.5 Haiku is the more affordable option for API usage.
Speed Comparison
Claude 3.5 Haiku generates output at 170 tok/s compared to GPT-5.1 Codex's 85 tok/s, and the time to first token is 100 ms for Claude 3.5 Haiku versus 400 ms for GPT-5.1 Codex. Claude 3.5 Haiku delivers faster throughput.
Verdict
For developers prioritizing affordability and speed, Claude 3.5 Haiku has the edge. For those who value coding and general intelligence and math, GPT-5.1 Codex is the stronger choice.
View Individual Model Pages
Claude 3.5 Haiku vs GPT-5.1 Codex — FAQ
Which is better, Claude 3.5 Haiku or GPT-5.1 Codex?
GPT-5.1 Codex wins on more benchmarks overall (10 vs 4). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude 3.5 Haiku compare to GPT-5.1 Codex for coding?
GPT-5.1 Codex is better for coding, scoring 78.0% on SWE-bench Verified compared to 22.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Claude 3.5 Haiku cheaper than GPT-5.1 Codex?
Yes, Claude 3.5 Haiku is cheaper. Claude 3.5 Haiku costs $0.80/1M input and $4.0/1M output tokens. GPT-5.1 Codex costs $1.3/1M input and $10.0/1M output tokens.
Which is faster, Claude 3.5 Haiku or GPT-5.1 Codex?
Claude 3.5 Haiku is faster, generating output at 170 tok/s compared to 85 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude 3.5 Haiku vs GPT-5.1 Codex comparison cover?
This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, GPQA Diamond, SWE-bench Verified, Output Speed, LiveCodeBench, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.