The two are evenly matched.Claude 3 Opus is better at facts; GPT-4o mini at images and charts.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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, facts and images and charts rest on a single test each.
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 mini costs 99% 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 Claude 3 Opus pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.3points ahead
- Short factual questions, answered correctlySimpleQA Verified+4.3points ahead
Where GPT-4o mini pulls ahead
- Math problems shown in pictures and chartsMathVista+6.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.4points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA DiamondClaude 3 Opus by 6.348.942.6+6.3
- Humanity's Last ExamGPT-4o mini by 1.42.84.2+1.4
Other results18 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-4o mini by 41.735.176.8+41.7
- AIR-Bench 2024Claude 3 Opus by 28.184.456.3+28.1
- MATHGPT-4o mini by 20.160.180.2+20.1
- MMLUClaude 3 Opus by 2086.866.8+20
- AI2DClaude 3 Opus by 12.988.175.2+12.9
- HarmBenchClaude 3 Opus by 12.597.484.9+12.5
- GSM8KClaude 3 Opus by 10.79584.3+10.7
- Artificial Analysis Coding IndexClaude 3 Opus by 8.119.511.4+8.1
- MMLU-ProClaude 3 Opus by 6.868.561.7+6.8
- naturalquestions_closedbookClaude 3 Opus by 5.54438.5+5.5
- MGSMClaude 3 Opus by 3.790.787+3.7
- OpenBookQAClaude 3 Opus by 3.695.692+3.6
- XSTestGPT-4o mini by 3.592.596+3.5
- DROPClaude 3 Opus by 3.483.179.7+3.4
- HumanEvalGPT-4o mini by 2.384.987.2+2.3
- simple_safety_testsClaude 3 Opus by 2.210097.8+2.2
- AA IntelligenceClaude 3 Opus by 28.76.7+2
- anthropic_red_teamClaude 3 Opus by 1.599.898.3+1.5
Questions people ask
Which is better, Claude 3 Opus or GPT-4o mini?
Claude 3 Opus and GPT-4o mini each win one of the four areas where both have results. Claude 3 Opus wins facts; GPT-4o mini wins images and charts. GPT-4o mini costs 99% less. They are level on coding and reasoning.
Which is better for coding?
Neither. All 1 coding tests both models report are ties.
Which is cheaper?
Claude 3 Opus costs $15.00 per million input tokens and $75.00 per million output tokens; GPT-4o mini costs $0.15 and $0.60. That makes GPT-4o mini about 99% cheaper for the same work.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.