GPT-4 Turbo is the stronger all-rounder.
Scores updated · 16 tests both models report · How we compare
Where each one wins
Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Reasoning rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
GPT-4 Turbo costs 56% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-4 Turbo pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+13.1points ahead
Where GPT-4 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- MATHGPT-4 Turbo by 40.883.342.5+40.8
- HumanEvalGPT-4 Turbo by 20.187.167+20.1
- MGSMGPT-4 Turbo by 1488.574.5+14
- GSM8KGPT-4 by 10.882.493.2+10.8
- Artificial Analysis Coding IndexGPT-4 Turbo by 8.421.513.1+8.4
- AIR-Bench 2024GPT-4 Turbo by 7.771.964.2+7.7
- DROPGPT-4 Turbo by 5.18680.9+5.1
- metr_hcastGPT-4 by 316.719.7+3
- naturalquestions_closedbookGPT-4 Turbo by 2.548.245.7+2.5
- MMLUGPT-4 by 2.471.173.5+2.4
- metr_swaaGPT-4 Turbo by 199.598.5+1
- OpenBookQAGPT-4 Turbo by 19796+1
- NarrativeQAtie76.176.8tie
- AA Intelligencetie76.7tie
- metr_re_benchtie00tie
Questions people ask
Which is better, GPT-4 Turbo or GPT-4?
GPT-4 Turbo wins the one area where both have results: reasoning. GPT-4 wins none.
Which is cheaper?
GPT-4 Turbo costs $10.00 per million input tokens and $30.00 per million output tokens; GPT-4 costs $30.00 and $60.00. That makes GPT-4 Turbo about 56% cheaper for the same work.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.