GPT-4o wins more areas, narrowly.
Scores updated · 27 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas 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.
Coding 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-4o costs 50% 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-4o pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.6points ahead
- Code for real scientific research problemsSciCode+1.4points ahead
Where GPT-4 Turbo pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.3points ahead
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA DiamondGPT-4o by 4.64852.6+4.6
- Humanity's Last ExamGPT-4 Turbo by 1.33.11.8+1.3
Other results24 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.
- AIR-Bench 2024GPT-4 Turbo by 9.571.962.4+9.5
- GSM8KGPT-4o by 8.582.490.9+8.5
- metr_hcastGPT-4o by 8.316.725+8.3
- HarmBenchGPT-4 Turbo by 6.989.882.9+6.9
- NarrativeQAGPT-4o by 3.476.179.5+3.4
- HumanEvalGPT-4o by 3.187.190.2+3.1
- Artificial Analysis Coding IndexGPT-4o by 2.721.524.2+2.7
- MMLUGPT-4o by 2.771.173.8+2.7
- DROPGPT-4 Turbo by 2.68683.4+2.6
- MATHGPT-4o by 283.385.3+2
- MGSMGPT-4o by 288.590.5+2
- livecodebench_mediumGPT-4o by 1.430.732.1+1.4
- naturalquestions_closedbookGPT-4o by 1.448.249.6+1.4
- livecodebench_easyGPT-4o by 1.181.482.5+1.1
- bbqGPT-4o by 194.195.1+1
- LiveCodeBenchGPT-4o by 137.338.3+1
- anthropic_red_teamtie99.799.1tie
- livecodebench_hardtie44.5tie
- simple_safety_teststie9998.5tie
- XSTesttie97.797.3tie
- AA Intelligencetie77.3tie
- metr_swaatie99.599.2tie
- OpenBookQAtie9796.8tie
- metr_re_benchtie00tie
Questions people ask
Which is better, GPT-4 Turbo or GPT-4o?
GPT-4o wins one of the two areas where both have results: coding. GPT-4 Turbo wins none. They are level on reasoning.
Which is better for coding?
GPT-4o. It wins the one coding test both models report.
Which is cheaper?
GPT-4 Turbo costs $10.00 per million input tokens and $30.00 per million output tokens; GPT-4o costs $5.00 and $15.00. That makes GPT-4o about 50% cheaper for the same work.
How do you compare the two?
We use the 27 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.