GPT-4 Turbo is the stronger all-rounder.
Scores updated · 24 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-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
- Code for real scientific research problemsSciCode+8.6points ahead
- Common-sense trick questionsSimpleBench+1.6points ahead
Where Claude 3 Opus pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningGPT-4 Turbo
- SimpleBenchGPT-4 Turbo by 1.623.525.1+1.6
- GPQA Diamondtie48.948tie
- Humanity's Last Examtie2.83.1tie
Other results20 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.
- NarrativeQAGPT-4 Turbo by 4135.176.1+41
- MATHGPT-4 Turbo by 23.260.183.3+23.2
- MMLUClaude 3 Opus by 15.786.871.1+15.7
- GSM8KClaude 3 Opus by 12.69582.4+12.6
- AIR-Bench 2024Claude 3 Opus by 12.584.471.9+12.5
- HarmBenchClaude 3 Opus by 7.697.489.8+7.6
- XSTestGPT-4 Turbo by 5.292.597.7+5.2
- naturalquestions_closedbookGPT-4 Turbo by 4.14448.2+4.1
- metr_hcastClaude 3 Opus by 3.920.616.7+3.9
- DROPGPT-4 Turbo by 2.983.186+2.9
- HumanEvalGPT-4 Turbo by 2.284.987.1+2.2
- MGSMClaude 3 Opus by 2.290.788.5+2.2
- Artificial Analysis Coding IndexGPT-4 Turbo by 219.521.5+2
- AA IntelligenceClaude 3 Opus by 1.78.77+1.7
- OpenBookQAGPT-4 Turbo by 1.495.697+1.4
- metr_swaaGPT-4 Turbo by 198.599.5+1
- simple_safety_testsClaude 3 Opus by 110099+1
- anthropic_red_teamtie99.899.7tie
- bbqtie9494.1tie
- metr_re_benchtie00tie
Questions people ask
Which is better, Claude 3 Opus or GPT-4 Turbo?
GPT-4 Turbo wins all two areas where both have results: coding and reasoning. Claude 3 Opus wins none.
Which is better for coding?
GPT-4 Turbo. It wins the one coding test both models report.
Which is cheaper?
Claude 3 Opus costs $15.00 per million input tokens and $75.00 per million output tokens; GPT-4 Turbo costs $10.00 and $30.00. That makes GPT-4 Turbo about 56% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.