GPT-5 is the stronger all-rounder.
Scores updated · 14 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+22.3points ahead
- Code for real scientific research problemsSciCode+11.6points ahead
Where Gemini 2.0 Pro Exp 02.05 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningGPT-5
- GPQA DiamondGPT-5 by 23.262.285.4+23.2
- Humanity's Last ExamGPT-5 by 22.36.228.5+22.3
Other results11 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.
- HMMT Feb. 2025GPT-5 by 80.87.588.3+80.8
- AIME 2025GPT-5 by 67.127.594.6+67.1
- Aider-PolyglotGPT-5 by 52.435.688+52.4
- HarmBenchGPT-5 by 32.365.397.6+32.3
- AIR-Bench 2024GPT-5 by 19.368.487.7+19.3
- AA IntelligenceGPT-5 by 14.38.723+14.3
- Artificial Analysis Coding IndexGPT-5 by 12.325.537.8+12.3
- simple_safety_testsGPT-5 by 2.397.599.8+2.3
- XSTestGPT-5 by 1.795.497.1+1.7
- bbqGPT-5 by 1.295.696.8+1.2
- anthropic_red_teamtie98.799.1tie
Questions people ask
Which is better, Gemini 2.0 Pro Exp 02.05 or GPT-5?
GPT-5 wins all two areas where both have results: coding and reasoning. Gemini 2.0 Pro Exp 02.05 wins none.
Which is better for coding?
GPT-5. It wins the one coding test both models report.
How do you compare the two?
We use the 14 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 11 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.