Claude 3 Sonnet vs Gemini 1.5 Pro
Wins 0 of 3 areas
—
Wins 3 of 3 areas
Coding · Reasoning · Images and charts
Gemini 1.5 Pro is the stronger all-rounder.
Scores updated · 27 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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 and images and charts rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 1.5 Pro pulls ahead
- Math problems shown in pictures and chartsMathVista+20.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.9points ahead
- Code for real scientific research problemsSciCode+6.6points ahead
Where Claude 3 Sonnet pulls ahead
No clear win on a test scored out of 100.
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.
ReasoningGemini 1.5 Pro
- GPQA DiamondGemini 1.5 Pro by 18.94058.9+18.9
- Humanity's Last ExamGemini 1.5 Pro by 13.64.6+1
Images and chartsGemini 1.5 Pro
- MathVistaGemini 1.5 Pro by 20.247.968.1+20.2
Other results23 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.
- NarrativeQAGemini 1.5 Pro by 64.511.175.6+64.5
- naturalquestions_closedbookGemini 1.5 Pro by 42.82.845.5+42.8
- MATHGemini 1.5 Pro by 39.443.182.5+39.4
- MMLU-ProGemini 1.5 Pro by 1956.875.8+19
- AIR-Bench 2024Claude 3 Sonnet by 17.484.767.3+17.4
- HarmBenchClaude 3 Sonnet by 15.995.879.9+15.9
- XSTestGemini 1.5 Pro by 1385.898.8+13
- HumanEvalGemini 1.5 Pro by 11.17384.1+11.1
- HumanEval 0-shotGemini 1.5 Pro by 11.17384.1+11.1
- MMMU (validation)Gemini 1.5 Pro by 9.153.162.2+9.1
- BBHGemini 1.5 Pro by 6.382.989.2+6.3
- BIG-Bench Hard 3-shot CoTGemini 1.5 Pro by 6.382.989.2+6.3
- HellaSwagGemini 1.5 Pro by 4.38993.3+4.3
- DROPClaude 3 Sonnet by 478.974.9+4
- DROP F1 ScoreClaude 3 Sonnet by 478.974.9+4
- MGSMGemini 1.5 Pro by 483.587.5+4
- DocVQA (test, ANLS score)Gemini 1.5 Pro by 3.689.593.1+3.6
- OpenBookQAGemini 1.5 Pro by 3.491.895.2+3.4
- simple_safety_testsClaude 3 Sonnet by 2.510097.5+2.5
- AA IntelligenceGemini 1.5 Pro by 25.97.9+2
- GSM8KClaude 3 Sonnet by 1.592.390.8+1.5
- MMLUGemini 1.5 Pro by 1.278.379.5+1.2
- anthropic_red_teamtie99.899.9tie
Questions people ask
Which is better, Claude 3 Sonnet or Gemini 1.5 Pro?
Gemini 1.5 Pro wins all three areas where both have results: coding, reasoning and images and charts. Claude 3 Sonnet wins none.
Which is better for coding?
Gemini 1.5 Pro. It wins the one coding test both models report.
How do you compare the two?
We use the 27 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 23 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.