GPT-4.1 vs GPT-4o: which is better?

GPT-4.1 leads on combined benchmark scores (88.4 vs 85.2) across general knowledge, coding, and math, as of 2026-07-27.

Which is cheaper, GPT-4.1 or GPT-4o?

GPT-4.1 is cheaper on a typical API workload, at roughly 1.3x lower cost than the alternative at published per-token rates.

GPT-4.1 vs GPT-4o

GPT-4.1 wins outright: higher benchmark scores and lower cost on a typical workload.

Updated 2026-07-27

GPT-4.1

OpenAI · Closed

88.4

Combined index

Leads

GPT-4o

OpenAI · Closed

85.2

Combined index

Benchmarks

General knowledge (MMLU)

90.2

88.7

Coding

91.5

90.2

Math

83.4

76.6

API pricing

$2.0 Input / 1M $2.5

$8.0 Output / 1M $10.0

$80.0 Monthly, est. $100.0

Monthly estimate assumes 20M input + 5M output tokens. Prices marked ~ are representative hosted rates for open-weight models and vary by provider. Run your own numbers in the cost calculator.

GPT-4.1 costs → GPT-4o costs → Full leaderboard → All comparisons →