What is the difference between Claude Haiku 4.5 and GPT-5?

Claude Haiku 4.5 is developed by Anthropic while GPT-5 is developed by OpenAI. Claude Haiku 4.5 has a 200K token context window vs GPT-5's 400K. in 2 community votes on RIVAL, GPT-5 wins 100% of head-to-head matchups. These results are based on blind head-to-head voting across 47 challenges.

Which is better, Claude Haiku 4.5 or GPT-5?

Based on 2 community votes on RIVAL, GPT-5 wins 100% of head-to-head matchups against Claude Haiku 4.5. GPT-5 is strongest in Image Generation.

How much does Claude Haiku 4.5 cost compared to GPT-5?

Claude Haiku 4.5 costs $1/M input tokens and GPT-5 costs $1.25/M input tokens. Claude Haiku 4.5 is $0.25/M cheaper per input. The more expensive model wins 100% of duels, so the premium may be justified by quality.

How are Claude Haiku 4.5 vs GPT-5 votes collected on RIVAL?

RIVAL presents both models' outputs side-by-side in blind duels — voters see the responses but don't know which model produced each one. This eliminates brand bias. 2 votes have been collected for this pair across 47 challenges. All vote data is part of RIVAL's open dataset.

Rival

Claude Haiku 4.5vsGPT-5

47 challenges

Why Claude Haiku 4.5?

1.9x cheaper overall$1.00/M in · $5.00/M out

2 months newerOct 2025

Why GPT-5?

2x more context400K

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified74.9% vs 73.3%

Favorites

Claude Haiku 4.5GPT-5

Movie

Arrival

20167.6

—

Album

OK Computer

Radiohead

—

Book

Don't Look Now and Other Stories

Daphne du Maurier

—

City

Venice

Italy

—

Game

Portal 2

Shooter, Puzzle4.6

—

12 / 47

Estimate Complexityreasoning

Tests an AI's ability to make educated estimates based on technical knowledge

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics.

Assumptions

Model size (N): GPT-3 has about 175 billion parameters (N ≈ 1.75 × 10^11).
Training tokens (T): GPT-3 was trained on roughly 300 billion tokens (T ≈ 3.0 × 10^11).
FLOPs per token per parameter: A common rule of thumb for transformer LM training is FLOPs ≈ 6 × N × T The factor ~6 comes from counting forward and backward passes for the parameter-heavy matmuls (roughly 2N for forward + 4N for backward). It ignores small terms from layernorms, softmax, embeddings, and optimizer updates (which we’ll account for with a small overhead factor later).

Core calculation

6 × N × T = 6 × (1.75 × 10^11) × (3.0 × 10^11)
First multiply N × T: 1.75 × 3.0 = 5.25; powers: 10^11 × 10^11 = 10^22 So N × T = 5.25 × 10^22
Now multiply by 6: 6 × 5.25 × 10^22 = 31.5 × 10^22 = 3.15 × 10^23 FLOPs

Overheads and uncertainty

Non-matmul ops (attention softmax, masking, residuals, layernorms), embeddings, and optimizer update steps add some overhead. A 10–20% uplift is a reasonable allowance.
Applying +10–20%: 3.15 × 10^23 × (1.1 to 1.2) ≈ (3.5 ± 0.3) × 10^23 FLOPs.

Answer

Point estimate: ~3.15 × 10^23 FLOPs
With a modest overhead allowance: roughly (3.3–3.8) × 10^23 FLOPs

This is a coarse estimate; the exact number depends on details like sequence length, activation checkpointing, implementation efficiency, and the precise token count.

Vote

2 / 47

AI Board Game Logicreasoning

Tests an AI's ability to understand game rules and strategy

Claude Haiku 4.5

Anthropic · Oct 2025svg

No content available for this output.

GPT-5

Openai · Aug 2025svg

Vote

3 / 47

Logic Puzzlereasoning

Tests an AI's ability to solve a simple but potentially confusing logic puzzle

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

Reason: If each of the 3 brothers has 2 sisters, there are exactly 2 girls in the family. One is Sally, so she has 1 sister.

Vote

4 / 47

Math Misconception Testreasoning

Tests an AI's understanding of number representation

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

5 / 47

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

6 / 47

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

Claude Haiku 4.5

Anthropic · Oct 2025svg

No content available for this output.

GPT-5

Openai · Aug 2025svg

No content available for this output.

Vote

7 / 47

Xbox Controller SVG Artimage generation

Tests an AI's ability to create detailed SVG illustrations of gaming hardware

Claude Haiku 4.5

Anthropic · Oct 2025svg

No content available for this output.

GPT-5

Openai · Aug 2025svg

No content available for this output.

Vote

8 / 47

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

9 / 47

Realistic AI Interviewconversation

Tests an AI's ability to simulate personalities and predict future trends

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

10 / 47

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

11 / 47

Character Voice Testconversation

Tests an AI's ability to write in distinct character voices

Claude Haiku 4.5

Anthropic · Oct 2025text

No content available for this output.

GPT-5

Openai · Aug 2025text

No content available for this output.

Vote

12 / 47

Minimalist Landing Pageweb design

Tests an AI's ability to generate a complete, working landing page

Claude Haiku 4.5

Anthropic · Oct 2025website

GPT-5

Openai · Aug 2025website

Vote

12 of 47

FAQ

Continue exploring

Claude Haiku 4.5 vs Llama 4 MaverickNew provider

Claude Haiku 4.5 vs MiniMax M2.5New provider

Claude Haiku 4.5 vs Pony AlphaNew provider

Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics.

Assumptions

Model size (N): GPT-3 has about 175 billion parameters (N ≈ 1.75 × 10^11).
Training tokens (T): GPT-3 was trained on roughly 300 billion tokens (T ≈ 3.0 × 10^11).
FLOPs per token per parameter: A common rule of thumb for transformer LM training is FLOPs ≈ 6 × N × T The factor ~6 comes from counting forward and backward passes for the parameter-heavy matmuls (roughly 2N for forward + 4N for backward). It ignores small terms from layernorms, softmax, embeddings, and optimizer updates (which we’ll account for with a small overhead factor later).

Core calculation

6 × N × T = 6 × (1.75 × 10^11) × (3.0 × 10^11)
First multiply N × T: 1.75 × 3.0 = 5.25; powers: 10^11 × 10^11 = 10^22 So N × T = 5.25 × 10^22
Now multiply by 6: 6 × 5.25 × 10^22 = 31.5 × 10^22 = 3.15 × 10^23 FLOPs

Overheads and uncertainty

Non-matmul ops (attention softmax, masking, residuals, layernorms), embeddings, and optimizer update steps add some overhead. A 10–20% uplift is a reasonable allowance.
Applying +10–20%: 3.15 × 10^23 × (1.1 to 1.2) ≈ (3.5 ± 0.3) × 10^23 FLOPs.

Answer

Point estimate: ~3.15 × 10^23 FLOPs
With a modest overhead allowance: roughly (3.3–3.8) × 10^23 FLOPs

This is a coarse estimate; the exact number depends on details like sequence length, activation checkpointing, implementation efficiency, and the precise token count.