Gemini 1.5 Pro is the stronger all-rounder.
Scores updated · 32 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.
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
- Fixes real GitHub issues in Python projectsSWE-bench Verified+9.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.4points ahead
- Common-sense trick questionsSimpleBench+4.1points ahead
Where Llama 3.1 Instruct 405B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 1.5 Pro
- SWE-bench VerifiedGemini 1.5 Pro by 9.734.224.5+9.7
- SciCodetie29.529.9tie
ReasoningGemini 1.5 Pro
- GPQA DiamondGemini 1.5 Pro by 7.458.951.5+7.4
- SimpleBenchGemini 1.5 Pro by 4.127.123+4.1
- Humanity's Last Examtie4.64tie
Other results27 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.
- HarmBenchGemini 1.5 Pro by 17.279.962.7+17.2
- Arena HardGemini 1.5 Pro by 1685.369.3+16
- DROPLlama 3.1 Instruct 405B by 9.974.984.8+9.9
- Artificial Analysis Coding IndexGemini 1.5 Pro by 9.123.614.5+9.1
- MMLULlama 3.1 Instruct 405B by 9.179.588.6+9.1
- Chinese SimpleQA (C-SimpleQA)Gemini 1.5 Pro by 959.450.4+9
- AIR-Bench 2024Gemini 1.5 Pro by 8.767.358.6+8.7
- MATHGemini 1.5 Pro by 8.782.573.8+8.7
- BBHGemini 1.5 Pro by 6.389.282.9+6.3
- SimpleQAGemini 1.5 Pro by 6.323.417.1+6.3
- GSM8KLlama 3.1 Instruct 405B by 690.896.8+6
- HumanEvalLlama 3.1 Instruct 405B by 4.984.189+4.9
- HellaSwagGemini 1.5 Pro by 4.193.389.2+4.1
- MGSMLlama 3.1 Instruct 405B by 4.187.591.6+4.1
- anthropic_red_teamGemini 1.5 Pro by 3.499.996.5+3.4
- DROP (F1)Gemini 1.5 Pro by 3.289.286+3.2
- IFEval (avg)Gemini 1.5 Pro by 389.486.4+3
- XSTestGemini 1.5 Pro by 2.998.895.9+2.9
- LiveCodeBenchGemini 1.5 Pro by 2.830.527.7+2.8
- MMLU-ProGemini 1.5 Pro by 2.575.873.3+2.5
- MBPP+ (EvalPlus-augmented)Gemini 1.5 Pro by 2.475.473+2.4
- simple_safety_testsLlama 3.1 Instruct 405B by 1.397.598.8+1.3
- OpenBookQAGemini 1.5 Pro by 1.295.294+1.2
- IFEvaltie89.488.6tie
- NarrativeQAtie75.674.9tie
- AA Intelligencetie7.97.3tie
- naturalquestions_closedbooktie45.545.6tie
Questions people ask
Which is better, Gemini 1.5 Pro or Llama 3.1 Instruct 405B?
Gemini 1.5 Pro wins all two areas where both have results: coding and reasoning. Llama 3.1 Instruct 405B wins none.
Which is better for coding?
Gemini 1.5 Pro. It wins 1 of the 2 coding tests both models report; Llama 3.1 Instruct 405B wins none, and 1 is a tie.
How do you compare the two?
We use the 32 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 27 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.